Two kinds of post. Feature releases say what changed for someone using Vocion. Developer updates say how it works underneath — schema, APIs, operations — and cite the files.
Prefer the short version? The release summary is one bulleted page. Subscribe by RSS.
Vocion 5.0 gives every person an assistant that asks their workspaces for them, organizes each workspace's work into apps, lets you decide by replying in Slack or by text, sets autonomy per action, and keeps a record of every run.
The software-factory plugin: a request becomes work a person approves from one card, a contract a headless worker executes in its own checkout, evidence QA checks against the contract, and a release the asker hears about. Three pages, four seats, gates at every handoff. vocion-core#655, #658, #672, #683, #695.
Three findings in twenty-four hours — 'approve' bound to the wrong record, a card narrated as a sentence, a card lost in the auto-file round trip — were each a seam between the pieces that make a card. What shipped: the card persisted on the turn and replayed to the model as the tool call it was, written down before it is filed. What is next: one typed card contract in core. vocion-core#690, #694.
Measured: 20m37s per deploy, 12m16s of it Next.js building on a 2-vCPU box. Now the image is built once on a CI runner, tagged by the core commit, skipped when the tag exists, and pulled by the box. A workspace-only deploy is 6m27s end to end; a core change about 17. Plus the twenty-minute rollback that taught the pipeline to refuse a superseded commit.
Handoff gates: a grammar declared on an object type's transition, a deterministic check that refuses and returns weak work to the seat that produced it, and a judge with the seat's own rubric that passes, returns with a reason code, or escalates to a person. Why the next seat is not the judge, why there is no second review product, and what the first reference runs measured. vocion-core#672, #683.
One room per engagement — a deal, a project — holding everything ingested about it and everything written from it: the sources filed with a weight and a score, the rules the agent reads first, the notes, the timeline, the open items on Review. A collector files clear matches after every sync and asks about plausible ones. What it is, who it is for, and the line that turns it on.
The client document written from its data room — proposals, scope documents, partnership updates — as print-ready sheets in the house framework that render-verify before a person sees them, are read as the sceptical buyer before the export will print them, and teach the writer a rule from every correction. What it is, who it is for, the line that turns it on, and what has changed since it shipped.
One line turns on a workspace's long-term memory: the voice, the standing rules, who is who, the decisions that hold — as markdown artifacts the agents write above a confidence bar, a researcher answers from, a debrief keeps current after every finished piece of work, and a curator consolidates on Fridays. What it is, who it is for, and what has changed since it shipped.
Per-product reference sets: synthetic inputs written the way a request actually arrives, real shipped commits as the gold standard, a standards page the seat reads and a dataset it never sees. The first set's baseline was 2 of 16 — and why that is the right number to start from.
The collector files fresh material into the room it belongs to, with its score and the evidence behind it, and a Remove that undoes it for good. It had never once worked in production — until today.
The red team stops being a habit the writer has to remember. export_document_pdf now refuses to print a client-facing document with a blocking finding on its current version — and reads the document itself if nobody has.
The Proposals plugin gains a red team, a twelve-sheet spine and its own learning step: the writer critiques the document the way the person receiving it will, and every correction becomes a rule the next proposal starts with.
The data-room collector shipped, ran after every sync, and filed nothing. One AND in a where-clause had pinned it to the sixty seconds around the run it followed — which made a documented constant unreachable and the dedupe code around it dead. vocion-core#463.
A client document cannot be exported until it has been read as the buyer. One Marketplace with two tabs is where you add capability; Teams is where you see what you already have. The Review queue calls a proposed action what it is — a recommendation. And the data-room collector files things, which it had never once done in production.
Two verbs, two places: Teams and Agents show the capability you already have, Marketplace is where you add more. And a Review item is now a recommendation — because a proposal is a document a client reads, not a decision on your queue.
The red team's first live run returned nothing parseable twice, and the agent read the document by hand instead and said so. The cause was a length budget, not a reasoning failure — and the fix was to stop asking a model for JSON in prose and declare a tool it has to call. vocion-core#457.
The screen where you decide what an agent recommended used to open with a restated subject, a confidence number and a paragraph of reasoning, and put the email two thirds of the way down. Now the email is the first thing on the page and renders as a composer, the decision is one sticky bar, and the note beside it changes the verb. vocion-core#466.
The new code started serving 40 seconds before the backup finished and 59 seconds before the last migration ran — and the swap that put it there killed every open stream. The rewritten flow migrates first, drains first, proves the new container is serving its own pin, and prints a receipt for each phase. It also found nine index builds that had never been applied.
The client-engagement workflow — one room per engagement, the document written from it — moves out of a sample workspace into two plugins with their own agents, missions and measures, and the sample workspace becomes one line plus a brand.
Vocion 2.117 ships workspace plugins — a wiki, data rooms and proposals as directories of agents, skills, pages, missions and measures that a workspace enables with one line, that the chat recommends when a conversation calls for them, and that start improving themselves the moment they are on.
What nine weeks of a founder's hand-run wiki taught us about long-term context for agents — and how Vocion's wiki plugin is built so the agents write it, people undo it, and nobody pastes into it.
A delegation that blew up rendered as "Delegating to the research specialist" forever, or as "the research specialist finished". The trace reader handled neither shape: a caught tool failure arrives as an ordinary end event carrying an error status, and an uncaught one arrives as a different event the reader had no case for. Four surfaces now say so — including after a reload, which used to rewrite every failure as a success. Release notes 2026-09-16 — vocion-core#368.
A decorative <kbd> showing a shortcut letter sat inside every decision button in the dashboard. Nothing marked it decorative, so it joined the accessible name: the Snooze button was called "Snooze s". A screen reader announced that, and a browser test clicking by exact name never matched — which is how a missing Snooze verb hid behind a failing test for a day. Release notes 2026-09-16 — vocion-core#367.
Eight fixes to the web connector and the candidate extractor, each found by running a real sync and reading the log. Listing-first crawl ordering, feed discovery scoped to the listing path, caps sized for one model call per document, a dry-run line that carries the dedup key, and a record that can no longer flag the card it is refreshing. Release notes 2026-09-16 — vocion-core#356, #362, #364, #365.
"Draft a pipeline report" used to come back as a sentence of narration and an empty pane, with no way to tell whether the agent decided against an artifact or simply forgot. Whether a turn ends in a document is now a typed field on the request, armed by typing @artifact — and a backstop guarantees one when the loop does not deliver. Release notes 2026-09-16 — vocion-core#368.
The Product Design Manifesto gains §18 and §19 — implementation is the forcing function, and extend the core while keeping the specifics at the edge. The pre-ship test grows from twelve questions to fifteen. Release notes 2026-09-16 — vocion-core#359.
Vocion's agents now carry typed, scoped memory — preferences, knowledge and procedures, filed per workspace, agent, user, mission or workflow. Every rule is a file a person can read and reword, approval is still the only way one is written, and approved rules finally reach the model instead of waiting to be noticed. Release notes 2026-09-16.
Search, Needs you, Artifacts and Learnings now render the same row. Search lost its form-and-cards layout for a one-line header, a single filter row that measures itself and folds what does not fit into a working dropdown, and a document detail page you can open, read and ask about. Release notes 2026-09-16 — vocion-core#339.
A workspace's voice used to be a paragraph in a prompt that nothing checked. It is now a typed rule set your workspace authors, enforced by a synchronous lint at every seam a draft can come through — the drafting model, the proposal, and the rewrite. A banned phrase costs the model one corrective retry and then fails loudly. And a phrase a reviewer cuts becomes a proposed rule. Release notes 2026-09-16 — vocion-core#370.
A record page now uses the whole window and the conversation rail overlays it instead of taking a column out of it. Bordered surfaces may no longer contain other bordered surfaces, with a dev-time warning when they do. And the rail no longer renders a second copy of what the page is already showing — it carries a pointer. Release notes 2026-09-16 — vocion-core#372 and #378.
The third release index in two days. The 2026-09-15 release branch lands on main and is cut as v2.82.0, alongside three lines of new work: scoped, typed, human-editable memory behind an approval gate; a web connector and extractor that are honest about caps, dedup and what a sync did; and the Slack thread surface, a second verified measure source, adaptive thinking on Claude 4.6+, and two new manifesto principles.
Six minor versions and four patches in one day, on top of the morning's 2.82. A structural gate on outbound copy, the briefing rebuilt as a typed document around the decisions only a person can take, four surfaces on one list row and a Search you can read, record pages at full width with a rail that points instead of repeating, @artifact as a typed contract on the turn — and the release train's leftovers finally cleaned up, including an accessibility bug that had quietly renamed every decision button in the product.
The morning brief used to be one markdown string a model wrote end to end, which meant every content rule — section order, whether an empty section renders, how many things may need you, whether "On track" is allowed next to "nothing ran" — was a sentence in a prompt. It is now a typed document with nine sections, an attention budget enforced in code, deltas joined against yesterday's brief, and system vocabulary moved into a footnote. Release notes 2026-09-16 — vocion-core#371.
One table behind a LangGraph BaseStore, scope carried in the key, a read-only filesystem mount, and a middleware that puts approved rules on the system message. Plus the migration renumbering the release train forced, and an honest account of the one write path the gate does not structurally cover. Release notes 2026-09-16.
A voice guide that asks for a register in the abstract is an instruction a model satisfies by performing the register instead of writing in it. That is where "Curious about…", "No pitch, just…" and "Quick question" come from — the guide's own words. The fix is not better wording: it is a schema refinement on the field the model fills in, a pure lint at three seams, and a retry budget of one. Release notes 2026-09-16 — vocion-core#370.
Superseded the same day. This describes the tile grid that shipped in the morning; by the end of the same day it had been replaced by a single live, versioned artifact. Release notes 2026-09-15 — vocion-core#333.
Mail the workspace and the lead answers in the thread. The inbound webhook verifies the raw body before parsing it, threading walks Message-ID then References then subject, and a stranger's mail becomes an ask instead of an agent turn.
Three archetypes cover every page the dashboard has. Here is what each one is for, how to tell a Ledger from a List, the anatomy of each, and the rule that new pages compose them instead of hand-rolling a layout.
Reports moved out of the daily driver, three pairs of pages became one page with tabs, and the engineer's door stopped living in everyone's nav. One registry now feeds the sidebar, the palette and the breadcrumb. Release notes 2026-09-15 — vocion-core#347.
Release notes 2026-09-15 — vocion-core#321 (merged): an action proposal carries suggestedDecision (approve, reject, snooze); the review API filters on it; adoption pairs the human's decision with the agent's advice. A reject recommendation can hold a run back from auto-execute, never release one.
The one row that promised a list delivered a blank composer. It opens a real list now. Plus: the header chat control closes as well as opens, and the autonomy rung stopped explaining itself in permanent UI. Release notes 2026-09-15 — vocion-core#353.
Rendered output stops being text in a transcript and becomes a row: an artifact table, render_* tools, first-party cards, and one org-checked route. Plus the operational lesson from a default that served files without asking who you were.
The conversation beside a page knows what page it is. Select a paragraph and ask about it, or press Do this to file a recommendation as a pending proposal. Release notes 2026-09-15 — vocion-core#329.
Release notes 2026-09-15 — outbound mail over Resend and the daily-team-report job (vocion-core#324, merged): what changed, what needs you, are we on track, what happens next — in your inbox, and as a Briefing in the app.
Release notes 2026-09-15 — vocion-core#318 (merged): approving or rejecting an agent-proposed action no longer writes a generated rule into the agent's learning step; it queues a candidate for the feedback classifier, deduplicated, for a person to accept.
Dump before you migrate and abort if the dump is empty. Log migrations one file at a time and then check that the tables they declared actually exist. Bump the pin by pull request, not by hand. The five practices, and the reasoning behind each.
Every decision a person makes in the review queue is written to a ledger. A six-rung ladder per action kind reads that ledger, and a promotion is refused unless the numbers are there. The thresholds, the schema, and how it maps onto trust.yaml.
Vocion had no notifications at all. It has one now — four tones, a pending state with a floor under it, and a rule that nothing on a decision screen advances before the server says it did. Release notes 2026-09-15 — vocion-core#351, #348.
Release notes 2026-09-15 — vocion-core#319 (merged): a knowledge source may declare a processor that runs once per changed document inside the sync, with its own budget and failure scope; the web connector reads feeds and URL lists; sources and budgets get v1 routes.
The team report used to tell you whether your agents ran. It now tells you what they produced against a target, where that number came from, how much of your own time it cost, and what it cannot prove. Release notes 2026-09-15 — vocion-core#350.
Release notes 2026-09-15 — vocion-core#323 (merged) adds a model override to evals and a comparison that reports pass rate, tokens and cost per passed case; GPT-6 Astra, the GPT-5.6 family and the Claude 5 family are priced in the catalog.
Release notes 2026-09-15 — the ask primitive and the Needs-you inbox (vocion-core#325, merged): approvals, rulings, merges and gates as one list with decision sheets, a recommended option, and an always-on Other.
There is no agent picker. A workspace has one lead, the specialists are a delegation roster derived from the org chart, and an @agent or @team tag routes a single turn without changing who you are talking to.
Release notes 2026-09-15 — the agent conversation is now a dock beside every dashboard page, open by default on a record, carrying the page you are on as context. The floating bubble is gone.
The agent rail is one surface on every page, fed by one typed event union over SSE. Here is the AgentEvent contract, the stream route, how a dropped connection resumes, and how a trace row gets drawn.
This morning the canvas was a grid of tiles. This afternoon it is one document open beside the chat, edited in place by you and by the agent, with a version for every change and a log of all of them. What the grid got wrong, and what replaced it. Release notes 2026-09-15 — vocion-core#354.
Review and Needs you were two doors onto the same job. They are one now: one list, one detail screen, one action bar, one keyboard map — whatever kind of decision it is. Release notes 2026-09-15 — vocion-core#348.
Release notes 2026-09-15 — docs/MANIFESTO.md (vocion-core#322, merged): seventeen principles, the loop Outcome → Work → Measure → Learn → Improve → Automate, the Outcome Contract every agent should carry, and a twelve-question test a change must pass before it ships.
What merged to vocion-core main and deployed on 2026-09-15 — the Needs-you inbox, outbound mail and the daily team report, the on-page conversation dock, recommended decisions, learning candidates, the extraction pipeline, per-workspace tool keys, the Slack surface, review-queue hardening, the Product Design Manifesto — the team report, the model upgrade test and Slack agent personas.
The second release of the day: Review folds into Needs you, the app gets its first notification surface, the nav sweep, a chat composer that never locks, a real conversations list, team report v2, a live versioned artifact — and the Claude 5 sampling-parameter outage that opened the afternoon and the two defects in its fix that closed it.
Release notes 2026-09-15 — a set of review-queue changes on vocion-core main since v2.5x: a failed execution is named and retryable, the queue filters by card type with true counts, Regenerate is an action capability whose feedback is a learning signal, and a run is claimed before it resumes so a double click runs it once.
Release notes 2026-09-15 — the Slack chat surface (vocion-core#251) is on main and deployed: app_mention and DM in, agent reply out, channels bound to agents, no Approve/Reject buttons in Slack yet. Updates our earlier post, which described it as in review.
Release notes 2026-09-15 — the team report (vocion-core#326, merged) reads worker runs against the org chart and states purpose, owner, KPIs, autonomy and spend weight per team and member; board and red-team runs are labelled as judgement.
The chat box used to go dead for the whole turn, which is exactly when you most want to add something. Now Enter queues, the queue drains in order when the turn lands, ⌘⏎ interrupts, and a stopped turn keeps what you typed. Release notes 2026-09-15 — vocion-core#352.
Every proposal in the Needs-you inbox is now described the way a person would describe it, grouped by the record it concerns, with a real age and columns that line up. Release notes 2026-09-15 — vocion-core#335, merged.
Every turn on a workspace 400'd because the harness still sent temperature. The one-line guard shipped in an hour. Writing it up found two defects in it, one of which silently made every default call non-deterministic. Release notes 2026-09-15 — vocion-core#346, #355.
The page where you decide what an agent proposed now says what you are looking at, folds the queue behind you out of the way, and keeps the decision in a bar that never scrolls off. Release notes 2026-09-15 — vocion-core#337.
A server component imported a helper from a 'use client' module. It crashed the page — but only after somebody answered a question, because that was the only state in which the component that used it rendered at all. Three bugs found by using the product. Release notes 2026-09-15 — vocion-core#349.
There is a clean checkpoint between the tool node and the next model call. You still cannot put a person's words through it, because of what the message list looks like at exactly that moment. The investigation, so nobody has to repeat it. Release notes 2026-09-15 — vocion-core#352.
Every dashboard URL was /dashboard/… and the workspace was a cookie, so a mailed deep link opened whichever workspace the reader last had active. The fix is a /w/<slug>/… entry route, and the plan after it is /{account}/{workspace}.
Release notes 2026-09-15 — vocion-core#316 (merged): web search, page fetch, crawling and image generation bill the workspace's own Tavily, Brave, Firecrawl or OpenAI key when one is stored, and the server's key only when none is. One definition of spendable; null and failure are different answers.
Running Vocion's marketing entirely on agents for 24 hours: one machine, four models, human-in-the-loop, every change a PR.
Why a chat interface is a new trust boundary, and the narrow Slack phase-1 slice now in review as vocion-core#238, not merged.
ADR 0004 is accepted on main; phase 1 (worker_run, the worker API, the reaper) is in review as vocion-core#237, a draft PR, not merged.
What self-hosting an agentic workflow platform ran in September 2026: Postgres, Temporal, Langfuse, an app server. Updated for 5.0: Temporal was removed in 4.0.
How to build an AI agent approval workflow you can self-host: an approve step, a skill that requires review, trust thresholds, and a REST decision API.
"AI agent registry" means two things: a discovery directory of running agents, and a versioned source of truth for agent definitions. Which one you need.
Which version of the agent did that? A concrete schema for AI agent versioning and audit trails: version rows on apply, a workspace SHA on every tool call.
When a human edits, approves, or rejects a draft, that decision can become a rule the agent reads next time — but only after a person approves it.
An agent can extract and score an application, but only a person should reject one. Here is the object, the gate, and the API call that enforces it.
Vocion's review queue API: GET /api/v1/reviews lists an org's pending agent actions, POST /api/v1/reviews/decide approves, rejects, or edits one.
Build a support agent that summarizes and drafts ticket replies, then holds them in a review queue until a human approves.
A guide to deploying AI agents in production with human approval: five insertion points, an autonomy ladder, trust thresholds, and a REST review queue.
The exact commands a coding agent runs to install Vocion, scaffold a workspace, apply it, and start the server, with a check that proves each step worked.
A small team wants shared agents, shared memory, BYOK and an autonomy dial. Here is what assembling it costs, and what one install still lacks.
A build guide with the artifacts: the agent file, the team file, the mission, the workflow with a human gate, and the version row the apply writes.
What to trace when many agents run: per-org, per-agent, per-feature cost, tool calls linked to a workflow, and the schema behind it.
What an open-source agent workforce platform is, what it must include, and how Vocion implements it with git-authored agents, approvals, and audit.
Autonomy levels are usually an analogy. Here are three real missions at levels 1, 2, and 3, the code that enforces the gate, and what the levels do not do.
v2.26.0 gives every lead a dedicated page at /gtm/lead/{hubspot_id} — the decidable card, the research record, and the decision trail on one addressable URL.
v2.25.0 lands review card contract v2 — subject, provenance, recommendation, typed content and per-object verbs — so any object type presents through one template and decides through one path.
v2.23.0 adds a Strapi connector that discovers your collections from a URL and a token, ingests many collections through one source, and survives a collection it cannot read.
v2.24.0 closes the API gap — fourteen new /api/v1 endpoints give review, feedback and learnings full parity with the dashboard, and admins can now mint API tokens without shell access.
A working setup for the v2.16 MCP surface in Claude Code: registration without leaking a token, exact CRM counts, on-demand call transcripts and mail threads, and writes that always wait for a human.
v2.16.0 serves the agent domain-tool registry over MCP — typed CRM reads, cache-aware Zoom transcripts and Gmail threads, knowledge search, and review-gated writes — plus a CLI for issuing Bearer tokens.
v2.15.0 gives agents three structured HubSpot read tools — one per object type — with exact COUNT(*) totals, discoverable facets, explicit pagination, and honest refusals when a field isn't synced.
Vocion now detects which of your recorded calls were discovery calls — without ever letting an agent read a transcript that didn't first match a CRM record you own. Plus: automations become inspectable, testable, and owned.
v2.3.0 ships the core base pack: versioned RevOps agents a workspace inherits with extends: core and overrides in YAML — with per-layer provenance and a guard that stops any override from loosening an approval gate.
The Jira connector lands — projects and issues as retrievable knowledge, hourly incremental — alongside per-source reconcile schedules: a second full-sync cadence, on every connector, that prunes what incremental syncs can never see deleted.
vocion-v2.1.5 makes agent chat legible and safe: a typed hierarchical Activity trace with tool drill-in, true token streaming, inline [n] citations with a two-level Sources drawer, recommended-action cards that land in human review, and a never-auto-send guard on outbound email.
The review queue becomes a focused one-at-a-time flow with editable, steerable actions — and briefings go team-scoped, with a workspace rollup, history, and live regeneration.
Teams become first-class: authored in YAML with a lead and an accountable human, rendered as an org chart at /dashboard/teams, consulted by the workspace lead in chat and missions, and seedable from a bundled sample workspace.
The first breaking release removes the bundled workspace from vocion-core. Workspaces now live beside the checkout as directories you own, scaffolded with one command and located via WORKSPACE_PATH.
Long-term memory lands: agents extract facts and preferences from past conversations and recall them in brand-new ones, with continuity that survives sessions.
The BYOA runtime ships the agent loop as a standalone artifact: one HTTP contract, hostable on a laptop in dev or AWS AgentCore Runtime in the cloud, with a CI deploy pipeline.
Restrict any source to specific members — enforced in chat and search as an intersection, never a leak. Plus e2e:demo — the full briefing + CRM sweep as an executable test, passing 9/9 against live production data.
Agents are who. Missions are goals. Workflows are procedures. Automations — new and first-class — are when. Plus: watch your agents actually think, with streamed chain-of-thought.
Mission checks now remember what they flagged (threads age across checks), high-confidence proposals can execute on enabled trust rules, workflows can ask a human for input mid-run, and briefings publish to their own page.
Missions are now charters a team owns continuously — checked on a schedule, discharged with only the work that's needed. Plus schedule triggers for workflows, agent steps, and an Automation page for every clock in your deployment.
Four verbs, no overlap: talk to the team, decide what needs you, observe everything it did, find anything. Activity is new — one feed for every check, run, fire, and sync.
Credential onboarding lands — paste a token or run one Google OAuth consent and your connectors sync for real. And agents gain propose_action: CRM updates and emails proposed with confidence scores, gated behind your review queue.
Vocion deployments are multi-user from day one — a Members page to see everyone, manage roles, and mint one-time invite links that need zero email infrastructure.
Agents now sweep the last 48 hours of email, detect what moved a deal forward or backward, and queue scored CRM updates for one-click human approval — the full loop, running on live HubSpot + Gmail data.
The write half of the runtime. A narrow, typed action (send an email, update a record) that an agent proposes and a human approves — the same permission model as everything else, now applied to mutation.
Agents now carry a role, a work mode, and a team — so a deployment reads as an org chart: one Lead you brief, its specialists doing focused work. A new Teams view makes it visible.
The trigger runner. An inbound event — a prospect reply, a meeting ending, a deal changing stage — fans out to the workflows subscribed to it, deduped and audited. The last load-bearing piece of the loop.
The second action on the framework — update a deal's stage, a contact's fields, a missing next-step — proposed by an agent, approved by a human, executed against the CRM.
Pending work now routes to a specific person — per-person queues, an unassigned triage lane, and snooze — so a workspace with many humans can actually divide the approvals.
The dashboard brand is now a slot — set a wordmark, a subhead, and your own glyph via build-time env, so a Vocion deployment wears your identity and the OSS build carries no one else's art.
The credential vault is now wired into the ingestion pipeline — a connector's OAuth/API credentials are stored encrypted-at-rest per tenant and resolved at sync time, so the connector pack can actually authenticate.
Two more waves of platform work shipped: tenant API tokens that resolve into the permission model (the control plane), and a connector pack — Google Ads, GA4, HubSpot, Gmail, Slack — on the durable, incremental ingestion pipeline.
The Drive connector — Docs, Sheets, Slides, and text files exported into scoped, retrievable knowledge — completes the connector set the two reference deployments run on.
We're building FirstHQ (an AI team HQ for agencies) on Vocion — and using it as a forcing function for the platform. Here's the architecture direction it's driving: scoped retrieval with document ACLs, durable ingestion pipelines, a discovery-vs-mutation permission model, and a clean split between the MCP tool plane and the API control plane.
The agent/tool plane goes multi-tenant. A single Streamable-HTTP MCP endpoint where the org is derived from a tenant Bearer token — every tool call scoped to that org, under the same permission model as a human.
A few days ago we wrote about the platform direction FirstHQ was forcing. Here's the first wave, shipped: client/team-scoped retrieval with document ACLs, a discovery-vs-mutation permission model with one review queue, and durable, resumable, incremental ingestion.
A source's schedule now actually fires — runSync runs inside a durable Temporal Workflow on a Schedule, so connectors keep their knowledge fresh on their own cadence, crash-safe and incremental.
The control plane gets its first write surface — the unified review queue, list and decide, on tenant Bearer tokens that resolve into the same permission model as a human.
v1.24.0 gives every agent a general toolbelt out of the box: live web search, page fetch + crawl, image generation, a safe calculator, and artifact creation. Providers are pluggable; defaults work with minimal setup.
vocion-v1.25.0 adds Missions: hand your AI team a goal in plain language and watch them plan it, split the work, produce artifacts, and pause for your approval. One Agent framework, three work modes. What works gets promoted into a Workflow.
Use SaaS for generic tasks. Use Vocion for the AI workflows you need to own, audit, and extend. Not anti-SaaS — anti-lock-in.
Vocion is open source under MPL-2.0, so your company can self-host it, modify it, embed it, and commercialize what you build on top. Open framework underneath; proprietary value on top.
Turn repeatable expertise into scalable, AI-enabled delivery — without removing human judgment. Which workflows are good candidates, and how the path works.
The fastest path to AI value isn't a brand-new process — it's improving a workflow your team already runs every week. A six-step way to do it.
The best AI workflows don't just save a few minutes — they change the operating model. Where AI creates leverage, and why the workflow matters more than the model.
A walkthrough of the v0.4.0 support-reply demo (two operations, one workflow, one card) — historical shape; see the staleness note before copying any YAML.
vocion-v0.3.0 ships ChatShell — a server-sent-events chat surface with 15s keepalives, thinking summaries, and inline tool calls. Here's how to use it and what's behind it.