Part of Visdom, VirtusLab's AI-Native SDLC
The organizational knowledge layer for AI coding agents: context your team never wrote down, served to any agent over MCP, inside your environment.
AI coding tools are fast and capable. What they produce compiles and passes tests, then breaks conventions, duplicates existing logic, and reverses deliberate decisions.
Every software organization holds two layers of knowledge. The syntactic layer, what the code does, is in the repository and any agent can read it. The semantic layer, why the code exists in its current form, lives in heads, review threads, postmortems, and tickets nobody reads twice.
A new developer knows what they don't know and asks. An agent doesn't. It sees incomplete context, treats it as complete, and fills the gaps with plausible-but-wrong assumptions. The bigger the organization, the more unwritten context exists, and the worse agents perform exactly where they would help most.
Read the full argument: The Hard Truth →What the agent works with
Each level answers a question an agent cannot answer from source code alone. Skip a level and a specific, predictable failure follows.
What ecosystem am I working in?
Services, dependencies, contracts, and infrastructure mapped into a living graph. Without it: the agent writes synchronous REST in a service whose contract is event-driven.
How do we write code here?
Conventions, linting rules, and recurring review feedback become reusable knowledge. Without it: the agent repeats the mistake your team corrected three months ago, every session.
Who owns this, and who must approve?
Actual reviewers, escalation paths, and approval policies per module. Without it: the PR merges technically and stalls politically, tagged to a reviewer who left weeks ago.
Why is it the way it is?
Decision records, review threads, and postmortems, surfaced when relevant. Without it: the agent "cleans up" a class shaped by a regulatory audit two years ago.
How does it behave in production?
Telemetry and incident history connected back to code generation. Without it: the agent optimizes in a vacuum, with no signal whether its changes helped.
Levels 1 and 2 are where most tooling stops. Levels 3 and 4 are where agents earn organizational trust, and where Context Fabric does the unglamorous integration work.
Context Fabric is infrastructure, not documentation effort. It builds the knowledge layer from systems you already run, and keeps it honest.
Signals from repositories, infrastructure code, PR history, tickets, and chat are compiled and merged into a single page per topic: one place where ownership, conventions, and decisions agree, with every artifact keeping provenance to its sources.
An agent describes its task and receives the smallest high-signal subset of context, within a token budget, tailored to planning, coding, or review. Delivered over MCP, or rendered as AGENTS.md and agent-specific rule files.
When a source changes, affected pages are rebuilt from their current sources, so stale facts simply stop existing. Drift is flagged in CI, contradictions are surfaced for curation, and humans can correct and lock any artifact.
Reviewer corrections feed back into the fabric: the knowledge layer learns what your seniors keep repeating.
Static rule files are a local maximum: siloed per agent, drifting silently, growing until nobody reads them. Context Fabric is query-centric: agents ask precise questions and get compact, current answers instead of re-searching raw documents on every task.
Delivery rides on proven standards, MCP tools and AGENTS.md files, so it works with Claude Code, Cursor, Copilot, or your own agents. Less discovery per session, fewer tokens burned, more accurate output.
The agent asks. Context Fabric answers.
# before touching services/payments context.system.dependencies("payments", direction="upstream") context.code.conventions(scope="services/payments") context.org.reviewers("services/payments", count=3) context.history.why("retry=7s on this endpoint")
Like every Visdom component, Context Fabric is deployed with your engineers and owned by your organization.
Review, testing, security, and governance all read the same ground truth, so agents and reviewers answer the same questions the same way.
The knowledge layer for planning, coding, and review agents. You are here.
Aggregates repos, tickets, docs, and PR history into one queryable ground truth.
Multi-layered pre-review for AI- and human-authored pull requests, in your CI.
Reads ownership, conventions, and test reliability. Findings return as reusable knowledge.
Architecture, property-based, and mutation testing beyond coverage metrics.
Sends test-reliability scores back, so review and agents trust the right tests.
Tamper-evident audit trail for every AI interaction across the lifecycle.
Every context query lands in the same signed ledger as the change it informed.
Runtime sandboxing and continuous AppSec validation for agent workflows.
Contains the agent while it works, scans the same pull request the review gates.
Build acceleration and selective testing so validation keeps agent pace.
Selects what to build and test from the fabric's dependency and blast-radius graph.
When a change reaches the risk gate, the same context does the deciding: trivial findings loop back to the agent, risky ones stop and wait for a human. AI Tracing signs every step.
Explore the whole platform at visdom.virtuslab.com
Deployment follows the Visdom engagement model: assessment first, a pilot with one team, then scale, component by component. Our engineers wire it in and hand over the keys.