Software for engineering organisations

Focused tools for software engineering organisations.

Five focused applications for the work of engineering — what AI coding agents do, controlled AI access to production, capability, AI instructions and intent.

Explore the products Get in touch

The product family

The problem

Engineering knowledge does not sit in one place

It is spread across repositories, documents, tickets, chat threads, instruction files and the people who remember. None of those is wrong on its own. Together they stop agreeing.

The cost is not dramatic, which is why it survives: an onboarding week that takes three, a coding assistant confidently applying a convention the team abandoned last year, a runbook whose numbers were true at the time somebody pasted them.

Five Teamcentric applications address those records.

The products

Focused tools for distinct problems

The applications stand on their own.

Fibre Available

Teamcentric Fibre

“What did our coding agents actually do?”

One live, searchable record of what your AI coding agents do on every machine: Claude Code and Codex read from their own records, any other compatible AI tool or LLM through the Fibre proxy. Replay any session change by change, follow a task from prompt to result, and check what the agents said against tests, builds and git.

  • Session replay: play, pause and step through every file change, side by side
  • Watchdog rules and Opengrep script analysis, with alerts to Slack, webhooks and your SIEM
  • Agents and models compared on the same work: tokens, cost, time and recurring failures
For
Security and compliance teams, engineering leads, platform and DevOps teams

Explore Fibre

Teamcentric Fibre Sessions: a session paused mid-way, with lanes for each task and a subagent, Files, Network, Scripts and Tokens rows above them, and below the playhead a file change shown side by side with line numbers.
Replay any session, change by change. Demonstration data.
Forge Closed beta

Teamcentric Forge

“Can our AI assistants see production without a shell?”

Forge agents give AI assistants read-only checks on your production machines over MCP. Every request needs a key limited to one link and the kinds of checks it was given, the machine itself has the last word, and every call is recorded. Agents connect out, so no inbound port is opened — and the same checks keep your technical documents true.

  • 65 read-only checks: fixed programs with fixed arguments, never a shell
  • Access keys with permission classes, shown once and expiring after 90 days
  • Documents and live dashboards that read their facts from the same systems
For
Teams using AI assistants, security and compliance, platform and operations teams

Explore Forge

Teamcentric Forge: an HR file server's checks grouped by family, each with its permission classes and result — web checks switched off in Forge, and three file checks disabled on the machine itself.
You decide what an assistant can check, and so does the machine. Demonstration data.
Skills Available

Teamcentric Skills

“Can we staff the work we have already promised?”

A live, shared picture of your engineering skills, connected to the work. People rate their own skills and their leads review them; project readiness, role fit, critical gaps and single points of failure are calculated live, and each person sees only their own reporting line.

  • Self-assessed and reviewed levels that fade until someone verifies them again
  • Twelve live reports, from project readiness to skill resilience
  • Every critical gap with a suggested action (train, mentor or hire) and a record of the decision
For
Heads of engineering, engineering managers, team leads, delivery leads

Explore Skills

The Teamcentric Skills dashboard: average project readiness, projects at risk with their reasons, the most critical skill gaps with a suggested action, data-health checks and stale skills.
Readiness, risks and critical gaps at a glance. Demonstration data.
Context Available

Teamcentric Context

“Are our coding agents working from the right instructions?”

One shared, governed library for the instructions, prompts and guidelines your AI coding agents work from — versioned, approved by knowledge layer and assigned to projects — and a CLI that writes the right version into every developer's folder and records who has which version, and where.

  • Artefacts with typed variables, attachments, dependencies and full version history
  • Approval by knowledge layer, and library updates each project takes change by change
  • A CLI for macOS, Linux and Windows that writes, checks and pulls — and never overwrites a local change without asking
For
Platform and developer-experience teams, team leads, security and compliance, developers

Explore Context

An AGENTS.md baseline artefact in Teamcentric Context: its Markdown rendered with variable placeholders highlighted, and panels for its facts, rating, usage across projects and an attached script.
Versioned, rated, and used in six projects. Demonstration data.
Blueprint Available

Teamcentric Blueprint

“Does this card say enough to be built from?”

Plan the work as a story map where a card carries the outcome it serves, its acceptance criteria, scope and constraints — then assemble that into a Markdown prompt instead of explaining it again in a chat window.

  • A fast story map — backbone, swimlanes, keyboard-accessible drag — and mind maps that generate one
  • Card intent: outcome, criteria, scope, constraints, references, open questions
  • A deterministic Markdown prompt with inherited architecture context, and an MCP endpoint for agents you scope
For
Product owners, engineering managers, tech leads, teams working with coding assistants

Explore Blueprint

The Teamcentric Blueprint board: search and filters above a story map whose columns are grouped into Discover and Deliver, with a Release 1 swimlane holding Must have and Should have rows of cards carrying a status and, where set, an assignee and an estimate.
A story map, cut off mid-column. Sample data.

Where they fit

Four arcs of one loop

Four of the applications cover different stretches of an engineering workflow. Fibre is not one of the arcs: it records what AI coding agents do across all of them.

Teamcentric does not do the implementation or the review — that is your team's work, and no tool should pretend otherwise. What it covers is the knowledge those stages depend on: who can do the work, what the work is for, what the tools have been told, and what the record says afterwards.

How we build

Claims that survive scrutiny

The five applications are designed for people who need to explain an answer, not merely repeat one.

The evidence stays attached
A readiness score leads back to reviewed levels, requirements and capacity. An applied instruction file leads back to its published version and the approval behind it. A generated fact leads back to its source and the time it was retrieved.
We do not guess about people
It would be straightforward to infer capability from commit history. We do not, because it would be wrong often enough to matter, and because people are entitled to know what their record says and where it came from.
Narrow and finished beats broad and nearly
Each product covers less ground than its category norm, and is more specific about what it does inside it. Every product page carries a list of what that product does not do.
We are direct about maturity
Fibre, Skills, Context and Blueprint are available. Forge is in closed beta. None is presented as more mature than it is.

Tell us what you are trying to work out

What your agents did last week, which document you keep correcting by hand, where your capability gaps are, how your AI tooling has drifted across repositories, or which piece of work loses its detail between the plan and the pull request. Every product is set up through a conversation rather than a signup form, so the specifics are genuinely useful.

Get in touch Why Teamcentric