Retainer
Managed AI Ops
The retainer that keeps the system healthy after the sprint. New features stay fixed-price change orders.
Read more →
Hephaestus Sprint - One system in production, in four to six weeks
A fixed 4–6 week project. We ship one RAG system or one agent into production, with a golden eval set, monitoring hooks, a runbook and a go or no-go to scale. It is a build, not a workshop.
One workflow
Tell us which system should go live
Internal RAG, a customer or support agent, or an ops agent. We say whether it fits four to six weeks, and what the fixed price is, before we start.
What we ship - Three variants
We pick one. The next system is another sprint, or a change order after this one is live.
- Internal RAG. Search and answers over your own documents, in your environment. People can see which source an answer came from.
- Customer or support agent. It reads the case, looks up the source, and drafts or takes the next step. It hands the case to a person when the step needs one.
- Ops tool-calling agent. It calls the tools you already use, with permissions, a log of each call, and a stop when the action needs a human.
How the four to six weeks go
Scope and price are fixed before we write the code.
1. Name the workflow
One system, one boundary, the people who will use it, and how we will know it is good enough. You get that in writing, with the price.
2. Build it in your environment
Private or VPC on AWS, Microsoft Azure, Google Cloud or GleSYS, or on-prem, by default. Data stays with you. Audit logs. We do not train on your data unless you ask us to, in writing.
3. Ship the evals with it
A golden eval set, a CI gate, monitoring hooks for quality, latency and cost, and a runbook: what it does, who to call, how to turn it off.
4. Go or no-go to scale
A written recommendation: keep it as it is, extend it under a new fixed price, or stop. Scaling is not assumed.
See Managed AI OpsWhat you leave with - The system, and the proof it still works
A demo is not the delivery. These ship with the system.
- Golden eval set. Real examples, agreed with you, that every later change has to pass.
- Monitoring hooks. Quality, latency and cost, so someone can see when it gets worse.
- Runbook. What it does, which data it touches, who to call, and how to turn it off.
- Go or no-go. A short written call on whether to scale, and what that next step would be.
Why a Hephaestus Sprint, not a workshop
You already know the workflow is worth trying. We put one slice of it into production.
- One system
- Internal RAG, a customer or support agent, or an ops agent. Not a roadmap of ten.
- Eval-native
- The golden set and the CI gate are part of the sprint. They are not a later phase.
- Senior, in Gothenburg
- The people who build it sit with automotive and connected-product teams when the work needs someone in the room.
After the sprint, or instead of it - Where this sits with the rest
The sprint is one system. Care, a coding setup, a person in the team, or a platform takeover are the other shapes.
Related insights - From pilot to production
How we think about shipping one system and knowing if it still works.
FAQ - Common questions
Short answers before you book a conversation.
Is this a workshop?
No. It is a build. At the end one system is in your production environment, with evals, monitoring and a runbook. We do not deliver a recommendation deck as the result.
What does it cost?
A fixed price, given before we start. It depends on the variant and on where it has to run. We do not publish a rate card.
Can you ship three agents in one sprint?
No. One system. The next one is another sprint, or a fixed-price change order once the first is live and the eval set exists.
What happens after week six?
You run it, your team runs it from the runbook, or we keep it healthy on Managed AI Ops. Scaling is a go or no-go, not an automatic next phase.
Where does the data stay?
In your environment. Private or VPC on AWS, Microsoft Azure, Google Cloud or GleSYS, or on-prem, is the default, with audit logs. We do not train on your data unless you ask us to, in writing.
Ready to scope it?
Bring the workflow, not a slide deck
We will tell you straight if it is one sprint, if it should be care of something you already have, or if we are the wrong people.
Let's talk about what you're building
