Home How it works Knowledge Sources
Source control for memory

Bring the knowledge your team
already trusts into Tenure.

AGENTS.md, Confluence, ADRs, READMEs, coding standards, and manual beliefs can all seed governed memory. Docs remain sources. Beliefs become the runtime state your AI can use.

Docs as sources

Keep your documentation.

Tenure does not replace AGENTS.md, ADRs, or Confluence. It turns stable parts of them into scoped beliefs with provenance.

Manual control

Create beliefs directly.

Teams can add explicit policies, conventions, decisions, preferences, and constraints without waiting for the system to infer them.

Safe adoption

Import does not mean inject.

Start in document-driven, observation, or curated modes so teams can review memory before models act on it.

Supported source types

Tenure starts from the knowledge you already maintain.

Most teams already have useful AI context. The problem is that it lives in scattered files, docs, and decisions that models cannot use consistently across tools.

#

AGENTS.md and CLAUDE.md

Use existing agent instructions as trusted source material, then convert stable guidance into scoped runtime beliefs.

Confluence and internal docs

Extract conventions, architecture rules, and team knowledge from documentation your organization already trusts.

ADR

ADRs and decision logs

Turn architectural decisions into model-facing state so future sessions inherit the why, not just the current code.

{ }

README and repo docs

Seed project-specific facts, setup rules, service boundaries, and codebase conventions.

Coding standards

Make lint preferences, testing rules, review expectations, and generated-code conventions available per turn.

+

Manual beliefs

Create explicit beliefs for policies, preferences, decisions, and constraints that should not depend on inference.

Markdown is a source

AGENTS.md is useful. It should not be the entire memory system.

Markdown files are great for human-readable instructions. Tenure gives those instructions governance, scope, provenance, review, and per-turn control.

Markdown-only memory

Everything sits in one file.

  • Hard to know what was actually used.
  • No per-turn audit trail.
  • Context grows stale unless manually curated.
  • Different tools may read different files.
Tenure memory

Docs become governed state.

  • Source docs remain linked as provenance.
  • Beliefs are scoped by user, team, project, or org.
  • Only relevant beliefs are injected per turn.
  • Teams can review, edit, pin, retire, or reject beliefs.
Manual belief creation

Some memory should be explicit from day one.

Teams should not have to wait for repeated conversations to establish known rules. Manual belief creation lets admins, team leads, and developers seed memory intentionally.

New belief
typedecision
canonical_namebilling_service_owns_invoice_state
contentThe billing service is the source of truth for invoice state.
why_it_mattersModels should not add invoice state writes to downstream services.
scopeteam:payments · project:billing-api
sourceADR-042 · created by human
Good manual beliefs
  • Architecture boundaries the model must respect.
  • Security policies that should override user preference.
  • Team conventions that are already settled.
  • User preferences that should persist across tools.
Better as docs only
  • Long procedural guides that should stay human-readable.
  • Reference material that changes constantly.
  • One-off troubleshooting notes.
  • Information the model should search, not assume.
Safe rollout

Start with trusted sources. Expand as trust is earned.

The fastest path is not “let AI learn everything.” It is to seed from sources you trust, observe what Tenure extracts, then approve the beliefs that should become runtime memory.

01

Import sources

Start with AGENTS.md, ADRs, coding standards, and Confluence pages that represent stable team knowledge.

02

Extract candidates

Tenure proposes structured beliefs with type, scope, confidence, source, and why-it-matters fields.

03

Review and approve

Pin, edit, reject, or approve before those beliefs become model-facing memory.

04

Inject per turn

Only relevant approved beliefs are injected into the model, with audit trails showing exactly what was used.

The practical adoption story: Keep the docs your team already trusts. Use Tenure to make the durable parts inspectable, scoped, and available across every AI client.

The point

Knowledge sources are where memory starts.
Beliefs are what the model uses.

Tenure lets teams seed memory intentionally, preserve source provenance, and decide exactly what becomes active AI context.