Ignix67

The platform that operationalises AI-first context-driven development. Ignix67 is currently in private beta with a small set of partner teams; the five capabilities below are the production scope for v1.

01.pr-review

PR Review

AI-assisted code review on every pull request. Reads the diff, applies your per-repo review rules, and posts threaded comments plus a reviewer vote in Azure DevOps.

Per-repo review rules from .ignix/review-instructions.md, loaded into every review
Severity-gated voting — HIGH blocks (-10), MEDIUM advises (+5), clean approves (+10)
Acceptance-criteria check against linked work items
Diff-only by design — no test execution, no AST, no SAST. Pairs with your CI, doesn't replace it.

02.work-items

Work-items intelligence

Natural-language access to your Azure DevOps work items. Query by ID or in plain English — the chatbot translates to WIQL, surfaces missing acceptance criteria, and shows what's blocking what.

Today: Azure DevOps (work items, queries, linked PRs)
AC compliance check during PR review against linked work items
Roadmap: Jira and Linear connectors

03.service-catalog

Service catalog

A queryable catalog of who owns what — services, contacts, tech stack — available to the chatbot and to other agents during planning.

Read the catalog in plain English ("who owns the payment service?")
Backs the planner so agents land work in the right repo with the right contacts
Roadmap: drift detection (catalog vs code reality)

04.wiki-indexing

Wiki indexing

Index your engineering wikis so agents and the chatbot can answer from what your team has already written. Event-driven: a wiki edit triggers re-indexing without a manual refresh.

Today: Confluence and Azure DevOps Wiki
Sliding-window chunks with overlap; deterministic IDs (idempotent re-ingestion)
Roadmap: Notion, GitLab Wiki, GitHub markdown

05.platform-assistant

Platform assistant

A chatbot that knows your platform — work items, code, wikis, service catalog, and your sky.net session history. Two-tier model: fast for tool calls, reasoning for genuinely complex questions, on the chatbot's own call.

Asks the right tool, escalates to a reasoning model only when the question deserves it
Can spawn a coding task from a description — same orchestrator that runs scheduled work
Web UI today; in-IDE and in-Slack on the roadmap

// trust model

Trust model.

Everything is a pull request, with logs, diffs, and artefacts attached. Runner pods are ephemeral and network-isolated — egress to Azure DevOps only. Scoped PATs, no broad credentials. Bounded autonomy: at most two correction cycles before a human is paged, and at most three clarification rounds before the planner forces a decision. The decider routes the happy path with deterministic code; LLMs only enter for genuinely ambiguous calls.

This is how Context-Driven Development looks operationalised. See the methodology →

// what it isn't

What it isn't.

Not an IDE copilot.
Not an auto-merge bot — humans merge.
Not a replacement for your test pyramid or your SAST.
Not a black box — every step lands as a PR with logs.

// access

Ignix67 is invite-only during private beta. If your team is shipping with AI assistance and you'd like access, send us a brief — we'll respond within a business day.

Request beta access →