Agentic engineering systems

Get more engineering out of your AI stack.

We help engineering teams ship faster, reduce rework, and lower AI costs by improving the systems around their coding agents.

+ The system around the agentFIG. 01

Task, code, docs, and team rules converge into relevant context. Context guides an agent workflow, with tests and human review leading to a review-ready change. Feedback informs the next run’s context and workflow configuration.

Illustrative engineering workflow — not a product interface.

Context. Workflows. Evaluation. Built around your stack.

A better way through

01 / The engineering challenge

Better models are only part of the equation.

The opportunity is not just generating more code. It is making the path from task to trusted change work better.

We work on the system around the model.

  1. 01

    Context gets lost.

    Agents can miss the conventions, decisions, and dependencies your engineers take for granted.

  2. 02

    Work gets repeated.

    Fragile handoffs, unclear checks, and poorly scoped tasks can turn apparent speed into review and rework.

  3. 03

    Spend is hard to explain.

    More tokens and more activity do not tell you whether useful engineering work is getting done.

02 / The system around the model

Make the whole
workflow work.

We connect the pieces that determine whether agents produce useful, reviewable work—and what that work costs.

01 / Context

Give agents the context that matters.

Structure repository knowledge, instructions, retrieval, and memory so agents can find relevant information without carrying everything into every task.

  • Knowledge sources
  • Retrieval
  • Context assembly
  • Freshness

What we build

Context map, retrieval changes, and maintainable agent instructions.

System design / Context02

Repository, documentation, and decision sources feed retrieval. Relevant material is selected into a scoped context packet with its provenance; other material stays in the source. Freshness checks keep the packet current.

Illustrative system designs

02 / Workflows

Turn one-off runs into repeatable workflows.

Design task boundaries, tools, handoffs, checkpoints, and recovery paths around the way your team actually ships software.

  • Task scope
  • Tools
  • Checkpoints
  • Recovery

What we build

A working workflow with clear checks, ownership, and failure handling.

System design / Workflows03

A task moves through plan, implement, and verify. Failed verification returns to implementation through a repair loop. Verified work crosses a distinct human approval boundary for human review. There is no automatic production deployment.

Illustrative system designs

03 / Evaluation

Know whether the changes help.

Test alternatives on representative engineering work. Track quality, human intervention, latency, and cost—not just agent activity.

  • Representative tasks
  • Checks
  • Traces
  • Comparison

What we build

An evaluation set, a comparison method, and a clear account of tradeoffs.

System design / Evaluation04

One fixed set of representative tasks branches into a baseline and a candidate. Both are compared against the same review criteria: quality, human effort, latency, and cost. No winning result is assumed.

Illustrative system designs

04 / Cost

Spend capability where it earns its keep.

Examine model selection, routing, context size, retries, and caching against the quality requirements of each task.

  • Routing
  • Context budget
  • Retries
  • Cost per outcome

What we build

A tested routing and cost-control policy, with explicit quality constraints.

System design / Cost05

Tasks with different needs are routed through routine, complex, or escalation paths. All three paths converge on the same acceptance checks. Routing is constrained by required quality, not just model price.

Illustrative system designs

03 / How we work

Improve one real workflow.
Then expand.

Start with a concrete bottleneck. Establish a baseline, implement a focused change, and evaluate whether it is worth taking further.

  1. 01

    Understand the system.

    Map the tools, repositories, context sources, checks, and handoffs around a representative workflow. Agree on what improvement would mean.

    Output

    A baseline and a focused problem statement.

  2. 02

    Build the intervention.

    Implement a targeted change with your team: better context, a more reliable workflow, stronger evaluation, or more deliberate model routing.

    Output

    Working code or configuration—not just recommendations.

  3. 03

    Evaluate and hand over.

    Compare the result with the baseline, document tradeoffs, and make the implementation understandable and maintainable.

    Output

    Evidence, documentation, and a clear next decision.

04 / Evidence over activity

Measure the work.
Not the hype.

We agree on measures that connect agent behavior to engineering outcomes. The goal is not maximum automation at any cost. It is useful progress with acceptable quality and effort.

Delivery
Elapsed time for comparable work, including waiting and rework
Quality
Acceptance checks, regressions, and review findings
Human effort
Corrections, interventions, and review time
Cost
Model and tool spend per accepted task, alongside human effort

Measures depend on the workflow and the quality of available data.

05 / A focused engineering partner

A specialist partner.
Not another platform to buy.

Peashoot works with engineering teams on the context, workflows, and feedback loops around coding agents. We start from your tools and constraints, then build and test changes against real work.

The people behind Peashoot

Brendan Duhamel

Software entrepreneur who has built and operated technology businesses internationally.

Cormac Duhamel

Software engineer working on agentic development at Chess.com.

Let’s find a better way through

Where is your engineering workflow getting stuck?

Bring a slow workflow, an unreliable agent, or an AI bill that is hard to explain. Let’s talk about what you want to improve.

Start a conversation