memco. Field Guide
Frontispiece Contents Read Appendices
i.
memco. The Memory Company · MMXXVI
An essay on

Agentic
Engineering
Memory

A field guide for engineering teams making AI agent work compound.

by Scott Taylor
with The Memory Company
scott@memco.ai
First Edition v1.0 May 2026
Begin reading →
ii. Epigraph ii.

One agent learns.
Every agent ships faster.

— Memco

iii. Preface iii.

Agentic engineering needs memory.

AI coding agents can now do real engineering work. The problem is that most teams do not keep what the work teaches them. An agent discovers a repo quirk, burns tokens on a dead end, gets corrected by a human, maybe solves the task, and then the lesson disappears into a session, PR comment, Slack thread, or local cache.

The next agent starts cold.

This guide is for engineering teams that want agent work to compound. It explains what memory is, what it is not, how to build it into the engineering workflow, and how to measure whether it is actually improving future work.

The shift we care about: from agents that complete tasks to engineering teams that retain what agent work teaches them.

Marginalia · For whom Written for engineering teams already feeling the friction —
  • CTO & VP Engineering
  • Heads of DevEx & AI platform leads
  • Staff and principal engineers
  • Engineering productivity teams
  • Founders building agent-heavy products
Plate I · The memory loop iv.
memory LIFECYCLE i. Capture ii. Distill + synthesize iii. Scope iv. Provenance v. Retrieve vi. Apply vii. Validate viii. Retire

Plate I The memory lifecycle in eight stages, after capture and before retirement.

Plate II · The second-run signal v.
WITHOUT MEMORY first run · second run · third run RUN 1 RUN 2 RUN 3 tokens evaporate every session WITH MEMORY each run feeds the next CONVERGES RUN 1 RUN 2 RUN 3 the team gets smarter, not the model

Plate II Without memory, every run pays full price. With memory, work converges.

Contents vi.
Table of

Contents

  1. i.The cold-start tax6 min
  2. ii.The second run is the signal5 min
  3. iii.What memory is not6 min
  4. iv.The memory lifecycle7 min
  5. v.The engineering brain5 min
  6. vi.Memory quality5 min
  7. vii.Memory fails when work changes6 min
  8. viii.Governance without killing speed5 min
  9. ix.The memory stack4 min
  10. x.Public commons memory6 min
  11. xi.Private, permissioned memory8 min
  12. xii.The 30-day memory pilot5 min
  13. xiii.The diagnostic toolkit4 min
  14. xiv.How teams evaluate memory5 min
  15. xv.Common concerns4 min
Open the full guide →
Appendix · Diagnostic tool vii.
One interactive tool

Appendix

The Field Guide should not just explain the problem. It should help teams find their own version of it.

  1. A.Memory Reliability LabMemory Reliability Score

A privacy-preserving, seven-minute diagnostic. Six dimensions, a rubric-based judge, and a written readout you can take back to your team. No repo access, no code upload, no proprietary data — pattern-level answers only.

A founder's note viii.

Most coding-agent demos show the first run.
The second run is the signal.

— Scott Taylor, Co-founder

Read the note →

Turn today's agent work into memory your company can reuse.

Run the Memory Reliability Lab

Tell us about one repo, one workflow.

The Memory Company memco.ai v1.0 · MMXXVI
Context is rented. Memory is owned.