Loop Engineering
How to design systems that launch coding agents themselves—and remain controllable
Slide contents
1. Loop Engineering
How to design systems that launch coding agents themselves—and remain controllable
2. IEEE styling does not confer IEEE status
What it is
A 2026 working note
A reformatted Orange Book
A practical playbook
What it is not
Not an IEEE publication
Not an Anthropic paper
Not a benchmark study
3. Engineers move from execution to loop design
Inside the loop
Give the next prompt
Watch every turn
Start work manually
Outside the loop
Define discovery
Design the evaluator
Keep stop points
4. The practice was named within one week
5. Loop sits one floor above the harness
Redrawn from HuaShu, Fig. 1 and Table I · PDF p. 2
6. Higher layers let errors survive longer
7. One turn passes through five required moves
Redrawn from HuaShu, Fig. 2 and Table II · PDF p. 3
8. Morning triage turns signals into reviewable PRs
Redrawn from HuaShu, Table II · PDF p. 3
9. Six parts implement five moves
Redrawn from HuaShu, Table III · PDF p. 4
10. Repeated runs do not make a loop
11. The hardest component must say no
Verify results, not confident self-reports
Treat reject as a normal outcome
Feed reasons into the next turn
Green tests do not mean right
12. Maker and checker must stay independent
Redrawn from HuaShu, Fig. 3 · PDF p. 4
13. The evaluator should act like a user
14. Full harness runs cost far more
Retro game · Opus 4.5
Solo · 20 min · $9
Full harness · 6 h · $200
Same prompt, different output
DAW · V2 harness
3 h 50 min
$124.70
Opus 4.6 · different prompt
15. The evaluator pays off beyond reliable solo
16. Every skipped move creates an anti-pattern
Redrawn from HuaShu, Fig. 4 · PDF p. 5
17. Deterministic gates surround LLM work
Redrawn from HuaShu, Fig. 5 · PDF p. 6
18. Scale holds; exact numbers depend on source
HuaShu · podcast retelling
1,300+ PRs / week
Wording: merged
Machine-written
Stripe Sessions · official
Over 1,000 / week
Shipped to production
Human review + approval
19. Three scheduler modes carry different trust budgets
Redrawn from HuaShu, Table IV · PDF p. 6 · June 2026 product snapshot
20. Four debts reinforce one another
Redrawn from HuaShu, Fig. 6 · PDF p. 7
21. Green PRs can hide a control failure
22. Discovery turns external text into control input
23. Autonomy requires bounded, reversible actions
24. Cheap generation makes judgment the bottleneck
25. Three disciplines preserve the right to refuse
26. Start with a small, complete loop
Redrawn from HuaShu, Table VI · PDF p. 9
27. The playbook hypothesizes; our eval supplies evidence
28. A loop should run itself— and remain stoppable
Book Cube
Working note, primary-source links, and new engineering research breakdowns are in the channel
Alexander Polomodov, Technical Director & Fellow, T-Technologies
@Book_Cube