Intelligence
A model is a component. We build the machine around it.
Harnesses, agents, memory, evaluation and the approvals that keep a person accountable. The model proposes; the system decides what is allowed to happen.
In use
The agents we actually run.
Not a catalogue of imaginary assistants. These are the systems working inside Wishflip today, described with their limits as clearly as their abilities.
Meyers_Ai
Coding specialist · built by Wayne Meyer
Meyers_Ai is a coding-specialist agent created by Wayne Meyer. It reads a codebase before it writes to one, prefers a failing test to a confident guess, and reports what it actually ran rather than what it intended to run.
- Reading an unfamiliar repository before changing it
- Running the test suite and reporting the real result
- Small, reviewable changes over dramatic rewrites
- Explaining a decision in plain language
- It does not deploy to production without an explicit approval step
- It does not hold credentials of its own
- It will say it does not know rather than invent an answer
How we build them
The harness, layer by layer.
AI harness engineering
The loop, the tools, the guardrails, the budget.
AvailableAgent design & orchestration
Roles, handoffs, and who is allowed to do what.
AvailableTool & workflow integration
Real systems with real permissions, not demos.
AvailableMemory & context systems
What an agent remembers, and what it is never told twice.
In developmentEvaluation & observability
Scores that mean something on Tuesday, not just launch day.
In developmentHuman approval & escalation
The moments where a person must be in the loop, by design.
AvailableMulti-agent collaboration
Agents that hand off work instead of arguing about it.
In development
Bring us a workflow that keeps breaking.
We will tell you whether it needs an agent, a script, or a person.
Start a project→