Writer (WRITER Agent / AI HQ)
Full-stack enterprise agentic-AI platform built on the Palmyra LLM family with graph-ba…
Full-stack enterprise agentic-AI platform built on the Palmyra LLM family with graph-based RAG, guardrails, and autonomous action agents. Raised $200M Series C at a $1.9B valuation (Jan 2026); Salesforce Ventures-backed; security-first architecture with audit trails — strong compliance fit.
Beta
Status
OAuth + audit-log polling
Pattern
Managed SaaS — nothing to install
Runtime
Not yet published
SDK version
Readiness
What “Beta” means for Writer (WRITER Agent / AI HQ)
The integration path is built and tested. Real customers can attach now, but expect minor breaking changes until the 1.0 contract freeze.
How it attaches
OAuth + audit-log polling.
Authorise Trustvice once via OAuth; Trustvice then polls Writer (WRITER Agent / AI HQ)'s audit-log API on a recurring schedule. No code changes.
Authorise Trustvice via OAuth so Trustvice can pull the platform's audit log on a recurring schedule. No code changes required.
- 1
Initiate the OAuth flow
Click “Connect” next to Writer (WRITER Agent / AI HQ) in Settings → Integrations. Trustvice generates a state token and PKCE challenge, then redirects you to the provider's authorize URL.
- 2
Authorise on the provider
Sign in to Writer (WRITER Agent / AI HQ) with an account that has audit-log read permissions and approve the requested scopes.
- 3
Trustvice schedules the poller
The callback exchanges the code for access + refresh tokens, encrypts them at rest, and schedules the first poll cycle (default 60–120 seconds).
- 4
Verify
Within a couple of poll cycles, audit entries land in Witness. The Integrations page shows last-poll timestamp, records ingested, and any errors.
# Dashboard navigates here: GET /api/oauth/authorize/writer?workspace=ws_abc123 # Trustvice 302s to the provider's authorize URL with PKCE, # the provider redirects back to: GET /api/oauth/callback/writer # Trustvice exchanges code → tokens → schedules the audit-log poller
Coverage
3 event types captured.
agent.invocationEvery top-level agent run — the input, the resolved output, timing, and token usage.
tool.callEach tool / function the agent invokes, with arguments and the returned result.
channel.messageMessages sent and received over the agent's channels (Telegram, Slack, Discord, …).
The full pattern guide
OAuth + audit-log polling — end to end.
Every framework on this pattern shares the same platform-side spine, endpoints, and gotchas. The pattern guide covers them in full.
Read the OAuth + audit-log polling guideNeed help landing Writer (WRITER Agent / AI HQ)?
Talk to the integration team.
We help you land the integration end to end — including the parts that live in your environment.
Request integration help
Trustvice 360