Jules

Engineer · AI usage, harness practices and where spend could have gone further.

Demonstration report. This engineer and their usage are synthetic.

This page is for the engineer and their manager to find cheaper defaults and harness fixes. It is never used to rank people.

Period

Summary

FY2027 to date

AI spend

$1,226

130 sessions · $9 each

Savings opportunity

$269

22% of spend, at list price

Practices on target

2 of 7

Focus: Knowledge MCP use, rtk coverage

Cache hit rate

82%

Team 82% · org 82%

FY2027 to date · estimated at list price

$269 of $1,226 spend

Largest saving first

Improve prompt caching$143
Cache hit rate 82% against an 85% target.
Keep stable context at the front of prompts and avoid switching models mid-session, so 85% of input reads from cache.
Right-size models$74
41% of routine spend ran on Opus: code research $66 of $159, documentation $58 of $153, ops $35 of $73, presentation $20 of $55.
Run docs, decks, ops and read-only research on Sonnet instead of Opus.
Keep context lean$39
9% of input tokens were past 100K of context.
Compact or /clear between tasks instead of carrying more than 100K tokens of context.
Route commands through rtk$13
63% of 1,109 Bash calls ran through rtk; 1.6M tokens of command output went into context.
rtk compacts test, build, git and search output before it reaches the model (about 70% smaller).

Compared with Social Publishing and the organization

Practice	Jules	Team	Org	Target	Recommendation
rtk coverage	63%Needs attention	63%	56%	≥ 80% of Bash calls	Install the rtk hook so test, build, git and search commands return compact output.
Knowledge MCP use	8%Off target	4%	30%	≥ 40% of sessions	Search the knowledge MCP before re-researching a codebase, and save findings back with remember.
Cache hit rate	82%Needs attention	82%	82%	≥ 85% of input	Keep CLAUDE.md and tool lists stable, avoid mid-session model switches, and resume sessions instead of restarting.
Context past 100K	9%On target	9%	10%	≤ 10% of input	On target
Opus on routine work	41%Needs attention	44%	44%	≤ 25% of routine spend	Default routine sessions to Sonnet and keep Opus for harness, design and hard debugging work.
Sessions using subagents	44%On target	46%	50%	≥ 30% of sessions	On target
Tool error rate	4.0%Needs attention	3.7%	3.0%	≤ 4% of tool calls	Fix recurring failures (permissions, env vars, flaky tests) in the harness rather than letting the agent retry.

Is the engineer moving toward the targets?

Month	rtk	Knowledge	Cache	Context	Model fit	Subagents	Savings opportunity
Feb 2026	–	–	59%Off target	9%On target	–	17%Needs attention	$15
Mar 2026	–	–	62%Off target	11%Needs attention	62%Off target	27%Needs attention	$32
Apr 2026	–	–	69%Off target	8%On target	62%Off target	32%On target	$22
May 2026	24%Off target	–	74%Needs attention	8%On target	55%Off target	42%On target	$37
Jun 2026	45%Needs attention	7%Off target	76%Needs attention	11%Needs attention	53%Off target	40%On target	$40
Jul 2026	67%Needs attention	9%Off target	81%Needs attention	8%On target	40%Needs attention	39%On target	$40
Aug 2026	69%Needs attention	8%Off target	79%Needs attention	10%On target	38%Needs attention	54%On target	$48
Sep 2026	68%Needs attention	8%Off target	86%On target	7%On target	30%Needs attention	46%On target	$15
Oct 2026	74%Needs attention	7%Off target	87%On target	10%Needs attention	27%Needs attention	51%On target	$20

FY2027 to date

By model tier, by month

Routine types (documentation, presentation, ops, code research) rarely need Opus

Cache reads are billed at a fraction of uncached input; a high share is what good caching looks like

Model	Requests	Uncached input	Cache reads	Cache writes	Output	Spend
Opus 5.5	1,629	6.4M	81.8M	5.6M	2.3M	$117
Opus 5	1,903	13.5M	93M	6.8M	2.8M	$227
Opus 4.8	1,533	13.8M	73.9M	5.6M	2.2M	$196
Opus 4.6	1,298	18.7M	53.5M	4.6M	1.9M	$196
Opus 4.5	41	1M	1.7M	173K	75K	$9
Sonnet 5.5	2,460	9.9M	128.9M	8.9M	3.5M	$90
Sonnet 5	3,101	22M	159.2M	11.6M	4.8M	$230
Sonnet 4.6	1,073	13.6M	48.8M	4M	1.7M	$96
Sonnet 4.5	24	606K	1M	103K	37K	$3
Haiku 5.5	3,661	14.1M	187.2M	12.8M	6M	$8
Haiku 4.5	1,791	13.8M	84.2M	6.3M	2.5M	$43
GPT Realtime (meetings)	129	1.3M	6.2M	483K	188K	$13
Total	18,643	128.8M	919.4M	66.9M	28.1M	$1,226

Spend and tokens come from LiteLLM gateway logs and imported agent session history, priced at API list rates.
Savings are estimates: routine Opus work repriced at the Sonnet available at the time; uncached input moved to cache reads up to an 85% hit rate; rtk removing 70% of unfiltered command output, which stays in context for about half the session's remaining turns; and 50% of input past 100K context avoided by compacting. Levers overlap, so the total is an upper bound.
rtk and the knowledge MCP are scored from their rollout (rtk May 2026, knowledge MCP Jun 2026).
Generated Oct 20, 2026, 7:46 AM.