How it works
Under the hood.
For you, or whoever does your due diligence.
Agentic Development Lifecycle (ADLC)
A team of AI agents does the work. You make the decisions.
How a request moves through the ADLC
- People
- AI agents
- Board and environments
Where people step in
The agents ask for a decision whenever they need one, and the preview environment waits for your review. You can also add or move work on your board, or ask the Concierge to tidy it, at any time. Nothing goes to production without your review, and production runs on the stack you choose.
- 01
Agree the priorities
You and your engineer pick the next work, its cost and how we know it is done.
- 02
Develop and verify
AI agents research, build and test it, then send it to a preview for you to try.
- 03
Review and release
Nothing ships until you approve it. Then it goes to production on your infrastructure.
Always on
- Tidy-up
- Refactoring finder
- Performance optimizer
- Opportunity researcher
Run loop
It finds customers and calls them. You take the warm ones.
01
Find leads
Agents research the market and find people who fit.
- Research
02
Follow up
On LinkedIn and by email, until they reply.
03
Call
An AI voice agent calls, and says it is an AI.
- Twilio
04
Hand over
Want a person? The call comes to you.
- You
05
Keep you posted
It messages or calls you when something needs you.
- Telegram
- Phone
Built with
The models and tools you already trust.
- ChatGPT
- Claude
- Gemini
- Qwen
- DeepSeek
- Mistral
- Llama
- Ollama
- Hugging Face
- PyTorch
- LangChain
- LangGraph
- CrewAI
- AWS
- Google Cloud
- Kubernetes
- Docker
- PostgreSQL
- Supabase
- Next.js
- Vercel
- GitHub
Trademarks belong to their owners. Listing them does not imply endorsement.
Who decides
Agents do the work. People keep the decisions.
| Action | You | Your engineer | AI agents |
|---|---|---|---|
| Set the priorities | Yes | Yes | |
| Research, build and test | Yes | ||
| Check every change automatically | Yes | ||
| Review risky or flagged changes | Yes | ||
| Approve a release to production | Yes | ||
| Find, follow up and call leads | Yes | ||
| Take the call when someone wants a person | Yes |
Questions
Cost, ownership and where it runs.
Do you always build new software?
No. If an existing product or integration solves the problem, we recommend that.
How much does it cost?
It depends on the outcome, so there is no price list. We agree a small first scope and its cost in writing before work starts. No hourly billing.
Who owns the code and the data?
You do. Code lives in your repository, and you control your data and accounts.
Where does the work run, and where does my data go?
Wherever your data needs to live: your cloud in the region you choose, your own servers, or our infrastructure. By default your data does not go to a public AI service.
What if the AI produces bad code?
Every change passes automated tests, a security scan and an AI review. Nothing reaches production without your approval.
What if my systems have no API?
We agree access first, then use exports or a person where there is no API.
Is there anything you won't take on?
Specialist or physical work. We bring in a specialist, or tell you up front.
Where this is going
Small teams achieving what once took entire organisations.
Book 15 minutes. Tell us what you want to build or what is slowing you down.