AI agents & automation

AI that does real work, with people approving what matters.

You do not need to replace everything to make work easier. Foundry 41 improves existing tools and processes, helps you decide where AI is worth using, and builds bounded agents and LLM features when they fit. Changes stay reviewable, and your team gets a clear handover.

Last updated

What we build

What kinds of AI work does Foundry 41 build?

Three kinds, all built so a person can see what the AI did and approve anything consequential.

AI AGENTS

Agents that do real work

An agent with a bounded job and scoped tools: it gathers, checks, drafts and prepares, then hands the result to a named person before anything consequential changes.

LLM INTEGRATIONS

AI features inside your product

Extraction, drafting, classification, search and assistants built into your application, with evaluation on agreed cases and fallbacks when the model is unsure.

AGENT-ASSISTED DELIVERY

Agents in the software pipeline

Agents that turn a spec into a pull request, with AI code review, human approval and monitoring around them. Details below.

Existing-business improvements

Untangle the work. Keep what works.

Bring the internal tool nobody likes, the repeated data entry or the handoff that always stalls. We work with the people doing the job, agree one useful change, and improve the existing setup rather than assume a replacement is needed.

UNDERSTAND

See where people get stuck

Trace one process, its exceptions and its tools. Agree a named owner and acceptance measures using your evidence, not an invented savings estimate.

FIX

Choose the simplest useful change

Improve an interface, connect tools or remove duplicate steps. Add AI only if it suits the task, data and risk; consequential actions retain human review. Agree access and provider boundaries before changes.

HAND OVER

Make the change maintainable

Test and review the change, document limitations and recovery steps, and hand over operating instructions to your named owner. Further work and support are optional, separate scopes.

Start with a short fit call, then agree a bounded improvement scope and fee before paid work. This is not a company-wide transformation promise, an automatic full rebuild or a guaranteed speed or savings claim. For a governed cross-system production workflow, the paid Workflow Blueprint defines the controls before implementation. Customer control of accounts, data and operating instructions does not change agreed software licenses.

Discuss what needs untangling

General AI advisory

Where would AI actually help your business?

Bring one bottleneck, not a mandate to automate everything. We look at the work as it happens today, including handoffs, source data, risks and the people who own the result. Sometimes the right recommendation is not to use AI.

The paid, bounded review ends with a written decision brief: a practical first test, its success and stop criteria, data-access and human-review needs, or a reason not to proceed. We agree scope and fee before the review. A prototype, implementation or ongoing advice is a separate engagement; a governed cross-system production workflow starts instead with the paid Workflow Blueprint.

Discuss one bottleneck

AI transformation consulting

How can your engineering team use AI without losing control of the work?

Start with one software-delivery path, not a company-wide transformation promise. We work with your engineers to identify where agents can help, what must remain legible to people, and how to check the result before and after release.

01 · MAP

Choose a bounded pilot

Walk through a real task from request to release. Identify repositories, data access, failure modes and the person accountable for the result.

02 · VALIDATE

Define what good looks like

Write acceptance criteria and representative evaluation cases. Agree automated checks, security review and the human decision points before an agent changes the workflow.

03 · OPERATE

Make the gates repeatable

Set a pull-request and release path, monitoring and rollback expectations, and a way for the team to review failures and adjust the process.

The deliverable is an agreed pilot scope and validation plan for your team's engineering process; implementation or coaching can be scoped separately. We agree scope and fee before paid work. If your goal is to replace a cross-system business workflow, we start instead with the paid Workflow Blueprint.

Discuss an engineering pilot

Agent-assisted delivery

How do AI agents help deliver software without skipping review?

We call it the Software Factory: AI agents working across software delivery without giving up review. Agents draft the change and open a pull request; every change then passes the gates a senior team would insist on: automated evaluation, AI and human code review, an explicit approval, a controlled release, and monitoring after it ships.

  1. 01 · Spec intake

    A person defines the change

    A written spec states the change and how it will be accepted. The agent works from the repository's own conventions, tests, and skills.

    Gate: accepted spec
  2. 02 · Build

    An agent opens a pull request

    The agent works on a branch in an isolated environment and opens a pull request with its reasoning attached. It never pushes to the main branch.

    Gate: pull request, not a direct push
  3. 03 · Risk gates

    Checks run on every change

    Tests, type checks, and workflow-specific evaluations run in CI; riskier changes need more review. Failures go back to the agent or to a person, not to production.

    Gate: checks pass
  4. 04 · Review

    AI review, then a human decision

    An AI reviewer flags likely correctness and security problems. A human engineer reads the diff and decides whether it merges.

    Gate: human approval
  5. 05 · Release

    Ship through your pipeline

    Approved changes release through the existing deployment path, with a known rollback.

    Gate: controlled release
  6. 06 · Monitor

    Watch it after it ships

    Logs, errors, and cost are watched after release. A regression becomes a new ticket and goes through the same gates.

    Gate: monitored in production

Internal reference: Sky, Foundry 41's own company brain, opens pull requests in our repositories. For a client, the agreed pilot scope or Workflow Blueprint sets which repositories, gates, reviewers, and release paths apply.

Control

How do you keep AI agents from doing the wrong thing?

By limiting what they can reach, checking what they produce, and putting a person in front of every consequential step. The controls are designed in from the start, not added after something goes wrong.

Company brains and governed workflows
  • 01
    Bounded access

    Scoped tools and credentials per job, read-only unless a write step is agreed.

  • 02
    Evaluation before release

    Agreed cases the agent or feature must pass before it goes live.

  • 03
    Human approval

    A named person approves anything that changes a system of record, a customer message, or production code.

  • 04
    Monitoring after release

    Errors, cost and quality are watched in production; regressions route to a person.

Questions

Frequently asked questions about AI engineering

What AI work does Foundry 41 do?

We improve existing software and business processes with AI only where it helps. AI build work includes bounded agents, LLM features and agent-assisted software delivery with evaluation and human approval. We also offer paid AI advisory for one business bottleneck and scoped engineering-team consulting.

Can you help us decide where to use AI?

Yes. Bring one business bottleneck. We agree a paid review scope and fee, map the process and constraints, and give you a written recommendation for a first test or for not using AI. Implementation is separate; a governed cross-system production workflow needs a paid Workflow Blueprint.

Do we need a new product or an ongoing retainer?

No. We can scope an improvement to the tools and processes you already use, without a new product or a mandatory retainer. We agree the change, acceptance checks, documentation and handover before paid work. AI is optional; ongoing support is separately scoped. A governed cross-system production workflow starts with a paid Workflow Blueprint. Software rights follow the agreed license.

What is an AI agent that does real work?

An agent with a bounded job, scoped tools and credentials, and a named person who approves consequential steps. It prepares, checks, drafts or changes things in your systems and leaves a record of what it did.

What is agent-assisted software delivery?

Agents take a written spec, work on a branch and open a pull request. Each change then passes automated checks and risk gates, AI code review, a human engineer's approval, a controlled release, and monitoring in production.

Do you offer AI transformation consulting?

Yes, for engineering teams with a specific delivery process to improve. We scope a pilot, define acceptance cases and review gates with your team, then agree separately whether to help implement or coach the rollout. For a cross-system business workflow, the paid Workflow Blueprint is the starting point.

Do the agents merge their own code?

No. Agents open pull requests; a human engineer reads the diff and decides what merges.

Which AI models do you use?

Whichever fits the task and your agreements. You hold the provider accounts and pay the providers directly, so the choice stays yours.

How do you know the AI is doing the job?

It is evaluated on agreed cases before release and monitored after. Failures and low-confidence results route to a person rather than into production.

Bring one bottleneck, task or workflow

What needs untangling?

Tell us what is slow, confusing or unreliable today, who owns the result, and whether you need a practical fix, advice, an engineering pilot or a build.