Decisions
graven in stone.

Not lost in chat.

You decide together. AI drifts as context grows.
Graven turns decisions into guardrails.

chat — acme/backend
You

Let’s not use Redis. LRU in-memory, 5-min TTL. We don’t need the complexity.

Agent

Agreed. LRU with Map-based approach, 5-min TTL.

· · · 130 lines later · · ·

Agent

Setting up Redis with ioredis and a connection pool

This happens every session. Every context switch. Every new chat.

Decision graph

Every decision connects.

Internal engine extracts relationships and assigns confidence weights to every edge. The graph returns not just what depends on a decision, but how strongly — scored with meaning-level similarity, co-occurrence frequency, and explicit references.

Change a decision — the agent sees ranked downstream impact before a single line of code moves.

decision · confirmedAuth: session-baseddecision · confirmedCaching: LRUdecisionRedis: rejectedconstraintToken rotation: 15massumptionCache-Control headersdecisionCDN: origin-onlylesson learnedIn-proc store OK⚡ blast radius: 2 affected

Every decision stays important.

Not in a doc nobody reads. In a system your agent checks before every change.

What changes

The agent stops guessing.

Closed questions stay closed.

The agent works inside the lines your team already set. Decisions, assumptions, constraints — one system.

Conflicts caught before code.

Two contradicting decisions? Flagged the moment they’re recorded. Not three sprints later.

Ask the graph, not the spec.

Your agent queries the exact decision it needs. No fifty-page specs in context.

See impact before the change.

Blast radius, conflicts, downstream effects — visible before a single line changes.

New chat, full context.

Agent opens a fresh session and instantly knows every decision, constraint, and where you left off.

Assumptions that know when they break.

Every assumption carries invalidation triggers. When the world changes, the system flags it.

Stop re-explaining.
Start building.

graven.ai© 2026 Graven