Ground every run in your own docs.
Paste in your ADRs, RFCs, and runbooks once. Stackon chunks and embeds them, then retrieves the most relevant pieces before each agent acts — so answers come from your team's decisions, not the model's guesses.
Third-party calls are capped at 60 rpm per token; retries use exponential backoff with a 3-attempt budget…
Refresh tokens rotate on every use; the prior token stays valid for a 30s grace window to absorb races…
On a 429 storm, shed load at the proxy before paging — the budget breach webhook fires automatically…
01
Ingest anything your team wrote down
Drop in an ADR, an RFC, a postmortem, a runbook — any text. Stackon splits it on paragraph boundaries into ~500-token chunks with a 50-token overlap, embeds each one with OpenAI text-embedding-3-small, and indexes the 1536-dim vectors in pgvector. Every chunk carries an optional citation so you always know where an answer came from.
Third-party calls are capped at 60 rpm per token; retries use exponential backoff with a 3-attempt budget…
Refresh tokens rotate on every use; the prior token stays valid for a 30s grace window to absorb races…
On a 429 storm, shed load at the proxy before paging — the budget breach webhook fires automatically…
02
Retrieved before the agent acts
Flip Use Knowledge on a canvas and every node runs against your index first. Stackon embeds the task, pulls the top six chunks above a 0.4 cosine-similarity floor, and prepends them as a Relevant team context block in the system prompt — instructing the agent to cite by source number when it leans on one.
03
Test retrieval before you trust it
A built-in search panel lets you query the index by hand and see exactly which chunks come back, each tagged with its similarity score and citation. No black box — you can read what the agent will read before you ever wire it into a run.
Third-party calls are capped at 60 rpm per token; retries use exponential backoff with a 3-attempt budget…
Refresh tokens rotate on every use; the prior token stays valid for a 30s grace window to absorb races…
On a 429 storm, shed load at the proxy before paging — the budget breach webhook fires automatically…
04
Trustworthy by construction
Sources and chunks are scoped to your team by row-level security, and every ingest is written to the compliance audit log. Each retrieval records the chunk IDs it used onto the run's trace span, so a grounded answer is auditable end to end — from the source you pasted to the span that consumed it.
text-embedding-3-small · 1536-dim
Embedding model
pgvector cosine · top-6 · min 0.4
Retrieval
~500 tokens · 50 overlap
Chunking
Part of one platform
Knowledge works hand in hand with Canvas & Missions.
Speed plus trust — prove your agents got better this week.
Knowledge is one piece of Stackon, the observability-first workspace for teams running Claude and Codex. Start free and instrument your first run today.