28 posts. Tags are topics; for the editorial split see Feature releases and Developer updates.
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.
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.
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.
"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.
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.
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.
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.
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.
Running Vocion's marketing entirely on agents for 24 hours: one machine, four models, human-in-the-loop, every change a PR.
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.
"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.
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.
Build a support agent that summarizes and drafts ticket replies, then holds them in a review queue until a human approves.
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.
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.
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.
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.
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.
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.
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.
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.