We've recently completed Phase 1 of a bespoke business valuation tool with James at Code23, and I've been extremely impressed. He has taken the time to understand both the commercial and technical requirements, communicated clearly throughout, and delivered a well-thought-out system with a high level of flexibility. The admin dashboard, in particular, gives us full control over the scoring and valuation logic, which was a key requirement. I'm looking forward to working with James on Phase 2 and would have no hesitation in recommending him to anyone looking for bespoke software development – Jason Atkins, Director, Lansley Commercial
AI development company for production agents & automation.
Production agents, automated pipelines and custom ML, including a logistics model trained on 13,371 real orders. Senior engineers direct the agents, enforce the evals and ship in days.
Key stats
2005
Established in Reading, UK
13,371
Orders modelled for Plastor ML
350+
Projects shipped
60+
Five-star Google reviews
Code23 agentic delivery vs traditional agency
Capabilities
Production agent systems
Senior engineers direct AI agents across architecture, code and review - the unfair advantage of a small team shipping at machine pace.
- Agentic Development
- Eval harnesses
- Claude API
- Production agents
Tool-using AI agents
Agents that call tools, follow policies and finish workflows your team already measures - scoped jobs, not open-ended chat.
- Tool-using agents
- Policy guardrails
- Eval harnesses
- Human review loops
RAG & grounded search
Retrieval tied to your documents, product data and permissions, with citations back to sources your team trusts.
- Document RAG
- Hybrid search
- Citations
- Access-aware retrieval
Workflow automation
Agent-backed pipelines replace brittle hand-offs so ops moves faster with an audit trail you can defend.
- Ops automation
- Compliance pipelines
- FastAPI & ML
- Observability
Selected work
How we engage
Project
Fixed-scope project
Scoped after Blueprint. Milestone payments. 90-day warranty on the build.
Start a projectPhased
Phased delivery
Discovery first, then build phases with clear gates. Scope locked per phase.
Map a phaseRetainer
Support retainer
Managed hosting, monitoring and continuous improvement from the team that built it.
See support tiersProcess
- 01
Map
Workflow, data sources, failure modes and the points that need a senior in the loop - pinned with the jobs you already measure.
- 02
Blueprint
Architecture, model choices, eval criteria and success metrics locked into a fixed-scope plan.
- 03
Build
Senior engineers direct agents across RAG, tools and product surfaces, with review on every merge.
- 04
Harden
Eval harnesses, security review and agent-led regression at machine depth against the gold set.
- 05
Launch
Staged rollout with monitoring, kill-switches and named ownership for the first weeks live.
- 06
Evolve
Prompts, tools and evals tuned against real usage - paths that miss the bar get cut.
What clients say
I have worked with Code23 and their team for over 5 years across 3 different projects ranging from mobile app development to custom WordPress websites. Together the team bring a level of expertise and professionalism I have not seen anywhere else... The results achieved have really helped to grow our business. I highly recommend their services to anyone looking for a custom project to be completed on time and in budget.
We have been working with James and the team at Code 23 for about 18 months now on a lengthy and sometimes complicated app development. At all times we have found Code 23 to be calm, competent, and their advice has been invaluable. The app is now live and we are extremely pleased with the results and are happy to continue our relationship with Code 23 for enhancements and hosting. We would be pleased to recommend Code 23.
Can't recommend these guys enough... really great service with expert advice. The technology they managed to integrate into our self service kiosk was outstanding and went the extra mile to make sure everything was as we wanted. Great job guys, i'll be engaging with Code23 for any future upgrades and add ons required TAN
It has truly been a fantastic experience working with the Code23 team. Every part of the process from the scoping and onboarding down to the design and implementation of our website was handled excellently. The quality of service delivered by the team is globally top standard and I couldn't be more satisfied with the final outcome.
The results of Code23’s hard work, professional approach, and ability to work together with us to create our vision, has resulted in an end product that we couldn’t be happier with. They have provided us with a fully rounded service, including plenty of support, advice, and guidance for the future too. We are all very excited to welcome our customers back to our wonderful new e-learning platform.
Questions about AI Development
What are the top AI development companies in the UK?
Judge on shipped production work, public reviews and whether seniors stay on the build. We are Reading-based, with 60+ five-star Google reviews and 350+ projects behind the AI practice.
How much does AI development cost?
Scope sets the number: workflows, data readiness, integrations and eval strictness. Blueprint defines the first release and we confirm current pricing against that agreed scope before Build begins.
How long does an AI project take?
Most first production releases run Map through Launch on a Blueprint timeline. Thin slices ship earlier; Harden and staged rollout protect go-live. Agents compress build; data readiness usually sets the critical path.
Do you build custom AI agents or only wrap ChatGPT?
Custom agents with tools, policies and evals. Commercial models stay in the mix where they fit - seniors design the system, agents execute the bulk.
Can you add AI into an existing product?
Yes. We retrofit agents, search and automation onto live stacks when the workflow and data support it. Greenfield is optional.
How do humans stay in control when agents ship at 5x speed?
Seniors set the brief, own architecture and hold the eval bar. Agents run under policies, harnesses and kill-switches - speed without that gate is not a release we ship.
Ready to put agents into production?
Tell us what you are trying to ship. We will map the first phase and a realistic budget.