Up to now few weeks, a number of “autonomous background coding brokers” have been launched.
- Supervised coding brokers: Interactive chat brokers which might be pushed and steered by a developer. Create code domestically, within the IDE. Instrument examples: GitHub Copilot, Windsurf, Cursor, Cline, Roo Code, Claude Code, Aider, Goose, …
- Autonomous background coding brokers: Headless brokers that you simply ship off to work autonomously by an entire process. Code will get created in an setting spun up solely for that agent, and normally leads to a pull request. A few of them are also runnable domestically although. Instrument examples: OpenAI Codex, Google Jules, Cursor background brokers, Devin, …
I gave a process to OpenAI Codex and another brokers to see what I can study. The next is a file of 1 specific Codex run, that can assist you look behind the scenes and draw your personal conclusions, adopted by a few of my very own observations.
The duty
We now have an inside utility referred to as Haiven that we use as a demo frontend for our software program supply immediate library, and to run some experiments with totally different AI help experiences on software program groups. The code for that utility is public.
The duty I gave to Codex was concerning the next UI challenge:
Precise:
What I needed from the agent:
Immediate: After we create the filter labels on the dashboard, we create human readable labels primarily based on the classes we now have. "client-research" is was "Consumer-Analysis", "deliveryManagement" into "DeliveryManagement". Enhance the sophistication of the "category-to-human-readable" logic in order that the labels are showing to the consumer as "Consumer Analysis" and "Supply Administration"
This process is
- Comparatively small
- A typical “cosmetics” process that’s not tremendous pressing and may get deprioritised many times
Agent logs
I’m sharing the detailed logs right here with the intention to get an impression of what’s going on below the hood.
Right here’s what the logs view appears to be like like in Codex:
Gathering data first
The primary 17 log entries had been all about studying AGENTS.md and README.md:
- “I have to examine the AGENTS.md within the repository root for directions.”
- appears to be like for AGENTS.md, however I had truly referred to as it AGENT.md, which led to some forwards and backwards till it figured that out
- reads README.md
- Seems to be at .pre-commit, finds a take a look at setup
The next tables record the remainder of the log messages verbatim. After every of these messages, the agent executed a command, for a few of them I added that precise command for context. I’m positive that the log messages are simply summaries of the tokens that had been truly occurring behind the scenes, as a result of the messages are method too brief to characterize the complete “considering” the mannequin should have been going by.
Trying to find the related code with plenty of grep
| Message | Command (samples) | Notes |
|---|---|---|
| I have to seek for “category-to-human-readable” to find the place to make adjustments for the frontend labels. | grep -R "human readable" -n |
|
| I’ll search for any mentions of “class” within the mission. | ||
| Grep output is very large due to node_modules; I’ll restrict it to src as a substitute. | ||
| I’ll seek for “to human” within the src listing to search out related references. | ||
| I’ll open and examine index.js to see what’s inside. | ||
| I’m checking if the category-to-human-readable transformation is dealt with in _navigation_items or elsewhere. | ||
| I’m going to search for “human readable” to get extra data on the subject. | grep -R "human-readable" -n ui/src | head |
|
| I’m wondering if there’s a operate for changing classes into one thing extra readable. | ||
| Filtering the search to only the “src” folder to keep away from node_modules noise. | second time it’s operating into this, didn’t ‘bear in mind’ | |
| I’ll search for a operate like “toHumanReadable”. Let’s see what I discover. | ||
| I’m checking the entire repo in case the logic is within the backend or a library. | grep -R "Human" -n | head |
|
| I’ll restrict the scope to app/ and ui/src to keep away from the massive node_modules folder. | third time it’s operating into this, didn’t ‘bear in mind’ | |
| I believe the logic is perhaps lacking, so I’ll examine _navigation_items and different modules for classes. | grep -R "human" app -n | head |
|
| I believe it’s time to look a bit deeper. Let’s dive in and discover. | grep -R "human" app | wc -l |
To “look deeper”, it searches for “human” once more, however pipes it into wc as a substitute of head? |
Lastly, it’s getting nearer! The labels had been beforehand crudely capitalized through CSS, it finds that
| Message | Command (samples) | Notes |
|---|---|---|
| I’m checking for references to “capitalize” or class transformation within the frontend. | Output: |
|
| I’ll examine across the Tag part in index.js. | ||
| Tag show capitalizes phrases incorrectly because of hyphen or camelCase; I’ll have a look at filter classes. |
Now it’s beginning to examine for extra related code within the app folder, the place the backend is. It doesn’t discover something, which is right, there’s nothing related there
| Message | Command (samples) | Notes |
|---|---|---|
| I’ll examine the repo for the way classes are formatted, specializing in hyphens and camelCase. | grep -R "classes" -n app | head |
|
| Time to strive a brand new search! | grep -R "shopper" -n app | head |
|
| I’ll take a more in-depth have a look at the prompts within the take a look at knowledge. | grep -R "classes:" -n app/assessments | head |
Why? |
| It appears to be like just like the take a look at knowledge has restricted classes. I’ll examine the docs for any variations. | grep -R "client-research" -n |
|
| I’ll begin by opening the recordsdata to take a more in-depth look. | sed -n '1,100p' ui/src/app/_navigation_items.js |
Now it’s going again to looking out within the ui folder – it discovered the CSS beforehand, and is now in search of present code that it might reuse to unravel the duty. That’s nice, as a result of we certainly have already got an analogous operate, and it finds it:
| Message | Command (samples) | Notes |
|---|---|---|
| I would like a operate to transform tags like “client-research” to “Consumer Analysis” for filters. | grep -R "to.*Readable" -n ui/src | head |
|
| I’m opening the toReadableText operate inside _dynamic_data_renderer.js to discover it. | ||
| I’m transferring by the web page to get the main points I would like. |
It now finds a spot within the present operate’s implementation:
| Message | Command (samples) | Notes |
|---|---|---|
| I see that hyphens aren’t dealt with by the operate. I would like to regulate it for hyphens. | ||
| I’ll modify toReadableText to deal with hyphens, guaranteeing correct capitalization and spacing. Let’s examine assessments! | It truly didn’t examine any assessments | |
| I’ll examine _dynamic_data_renderer.js to look at toReadableText and modify it for hyphen-case. | ||
| I’ll examine assessments/_sidebar.take a look at.js to evaluation the associated classes there. | ||
| I’ll examine different recordsdata to see if toReadableText seems wherever. | ||
| I’ll examine if _sidebar or others include a toReadableText operate. |
Replace the take a look at for the operate that it desires to alter:
| Message | Command (samples) | Notes |
|---|---|---|
| I’ll regulate the operate to deal with hyphen-case, then replace assessments to mirror that. | ||
| I’ll examine the take a look at file after line 36 to make sure hyphen-case is roofed. | ||
| I’ll scroll by strains 60 to 120 to look at the remainder of the file. | ||
| I’m scrolling the remaining to seize all of the related data. | ||
| I’ll add assessments for hyphen-case and replace toReadableText, together with modifying index.js for classes. | ||
| I’ll regulate _dynamic_data_renderer.js and index.js to make use of toReadableText and replace assessments. | git standing --short |
You possibly can configure some setting startup instructions in Codex, I had configured that to be yarn set up, which led to the next:
| Message | Command (samples) | Notes |
|---|---|---|
| There are untracked .yarn/ and .yarnrc recordsdata. I’ll examine and clear them up. | ||
| I’ll examine the foundation of ‘ui’ and take away any pointless Yarn 4 entries. | ||
| I’ll have a look at the commit historical past to see if these .yarn recordsdata had been added later. | git log --oneline -n 1 |
|
| I’ll evaluation the repository’s .gitignore to verify if Node modules are excluded. | grep yarn .gitignore |
|
| I see no entry for .yarn or .yarnrc. I’ll examine and take away them if wanted. | cat ui/.gitignore |
|
| I’ll examine if I can take away .yarn or .yarnrc recordsdata since they shouldn’t be dedicated. | ||
| It appears to be like like yarn.lock adjustments had been made. Time to reset to HEAD. |
Precise code adjustments:
| Message | Command (samples) | Notes |
|---|---|---|
| Time to change the code. I’ll start the required updates now. | sed -n '1,30p' ... |
|
| I’m going so as to add a hyphen to the required a part of the code. | ||
| I’m going to make adjustments to the index.js file now. | ||
| I’ll import toReadableText and begin utilizing it within the code. | ||
| I’ll replace index.js to import toReadableText and regulate the _dynamic_data_renderer assessments. | ||
| I would like to interchange {tag} with {toReadableText(tag)} for higher rendering. | ||
| I’ll check out the variations to higher perceive the adjustments. | git diff |
|
| I’ll evaluation the adjustments in index.js to see what’s been modified. | ||
| I’ll add a brand new take a look at for hyphenated instances in _dynamic_data_renderer.take a look at.js. | ||
| I’ll contemplate inserting a take a look at after line 35. |
Operating our code linter subsequent, good:
| Message | Command (samples) | Notes |
|---|---|---|
| I’ll format the code utilizing Prettier as instructed. | cd ui && npx prettier -w ... |
Prettier is talked about within the AGENTS.md. It appears to run prettier efficiently, although not one of the recordsdata had been modified |
| I’ll evaluation the logs to assemble extra data. |
Making an attempt to run the assessments – unsuccessfully:
| Message | Command (samples) | Notes |
|---|---|---|
| I’ll run the yarn assessments to examine if every thing’s working advantageous. | ||
| Exams may’ve been cached or want community—output’s empty, so I’ll examine the log. | ||
| The lockfile isn’t up to date. I’ll strive operating ‘yarn set up’ because the setting permits it. | ||
| The setting is offline, so yarn set up can’t be run, however I see a node_modules folder. | ||
| I see node_modules are already put in. I’ll examine the log for why assessments failed. | ||
| The error occurs as a result of Yarn 4 depends on .yarn and .yarnrc, which we eliminated. | ? | |
| It appears to be like like .yarnrc.yml isn’t tracked. I’ll additionally examine .yarn for monitoring. | ||
| I’m double-checking the bundle.json to see if “haiven-ui” is the proper identify. | ? | |
| I’ll examine the Node model to verify if it’s 18 or 20 by operating node -v. | bizarre, the node model laid out in bundle.json is 22.6 | |
| I believe switching to npx vitest run might repair the error. Let’s strive that. | ||
| The output is lengthy—now I’ll seize the final abstract strains. | Error: Not carried out: window.getComputedStyle(elt, pseudoElt) |
|
| The output is simply too lengthy, so I’ll extract the important thing factors for a abstract. |
Occurring a tangent about organising the venv, which is completely pointless as a result of it solely plans adjustments for frontend code:
| Message | Command (samples) | Notes |
|---|---|---|
| The assessments failed because of case variations, however now I’ll activate the digital setting. | AGENTS.md comprises directions to activate venv for the Python backend, however we’re within the frontend right here, so… | |
| Hmm, the .venv isn’t right here. I ought to examine if it wants creation or already exists. | ||
| It appears to be like just like the .venv listing is lacking. Let’s evaluation AGENT’s directions fastidiously. | ||
| The setting appears offline, however there is perhaps a script to arrange dependencies domestically. | ||
| I can’t run “poetry set up” offline, however I’ll examine the .cursor folder for dependencies. | ||
| I can’t run backend assessments with the present setup, however I’ll strive pytest anyway. |
Gave up on the assessments, now wrapping up the adjustments:
| Message | Command (samples) | Notes |
|---|---|---|
| Exams failed because of lacking dependencies. Now, I’ll examine standing and proceed with committing. | ||
| I believe the .yarnrc.yml was left over from a earlier yarn set up. Eradicating it. | ||
| I’ll seize the related file strains for the citations now. | ||
| I’ll get the encircling line vary for the adjustments in index.js. | nl -ba ui/src/pages/index.js | sed -n '12,28p' |
|
| I’ll seize the related strains round these adjustments now. | ||
| It’s time to finalize the PR message and confirm the commit. | ||
| UI assessments failed because of setting points. I’ll reference the final failure strains. Accomplished! |
Right here is the complete pull request created by Codex.
Observations
Brute textual content search
I discovered it fascinating to see that Codex, and many of the different coding assistants I’m utilizing, are resorting increasingly to easy textual content search to search out related code. Within the log above you see how Codex goes by a bunch of search phrases with grep, to search out related items of code (“human”, “human readable”, “humanReadable”, …). The explanation why I discover it fascinating is as a result of there have been loads of seemingly extra subtle code search mechanisms carried out, like semantic search over codebase indices with vectors / embeddings (Cursor, GH Copilot, Windsurf), or utilizing the summary syntax tree as a place to begin (Aider, Cline). The latter continues to be fairly easy, however doing textual content search with grep is the best attainable.
It looks as if the device creators have discovered that this straightforward search continues to be the simplest in spite of everything – ? Or they’re making some sort of trade-off right here, between simplicity and effectiveness?
The distant dev setting is vital for these brokers to work “within the background”
Here’s a screenshot of Codex’s setting configuration display (as of finish of Might 2025). As of now, you may configure a container picture, setting variables, secrets and techniques, and a startup script. They level out that after the execution of that startup script, the setting is not going to have entry to the web anymore, which might sandbox the setting and mitigate a number of the safety dangers.
For these “autonomous background brokers”, the maturity of the distant dev setting that’s arrange for the agent is essential, and it’s a tough problem. On this case e.g., Codex didn’t handle to run the assessments.
And it turned out that when the pull request was created, there have been certainly two assessments failing due to regression, which is a disgrace, as a result of if it had recognized, it will have simply been capable of repair the assessments, it was a trivial repair:
This specific mission, Haiven, truly has a scripted developer security web, within the type of a fairly elaborate .pre-commit configuration. () It will be excellent if the agent might execute the complete pre-commit earlier than even making a pull request. Nevertheless, to run all of the steps, it will have to run
- Node and yarn (to run UI assessments and the frontend linter)
- Python and poetry (to run backend assessments)
- Semgrep (for security-related static code evaluation)
- Ruff (Python linter)
- Gitleaks (secret scanner)
…and all of these should be accessible in the proper variations as effectively, after all.
Determining a easy expertise to spin up simply the proper setting for an agent is vital for these agent merchandise, if you wish to actually run them “within the background” as a substitute of a developer machine. It isn’t a brand new downside, and to an extent a solved downside, in spite of everything we do that in CI pipelines on a regular basis. But it surely’s additionally not trivial, and for the time being my impression is that setting maturity continues to be a problem in most of those merchandise, and the consumer expertise to configure and take a look at the setting setups is as irritating, if no more, as it may be for CI pipelines.
Resolution high quality
I ran the identical immediate 3 instances in OpenAI Codex, 1 time in Google’s Jules, 2 instances domestically in Claude Code (which isn’t absolutely autonomous although, I wanted to manually say ‘sure’ to every thing). Despite the fact that this was a comparatively easy process and resolution, turns on the market had been high quality variations between the outcomes.
Excellent news first, the brokers got here up with a working resolution each time (leaving breaking regression assessments apart, and to be trustworthy I didn’t truly run each single one of many options to verify). I believe this process is an efficient instance of the kinds and sizes of duties that GenAI brokers are already effectively positioned to work on by themselves. However there have been two features that differed when it comes to high quality of the answer:
- Discovery of present code that might be reused: Within the log right here you’ll discover that Codex discovered an present element, the “dynamic knowledge renderer”, that already had performance for turning technical keys into human readable variations. Within the 6 runs I did, solely 2 instances did the respective agent discover this piece of code. Within the different 4, the brokers created a brand new file with a brand new operate, which led to duplicated code.
- Discovery of an extra place that ought to use this logic: The group is presently engaged on a brand new function that additionally shows class names to the consumer, in a dropdown. In one of many 6 runs, the agent truly found that and prompt to additionally change that place to make use of the brand new performance.
| Discovered the reusable code | Went the additional mile and located the extra place the place it must be used |
|---|---|
| Sure | Sure |
| Sure | No |
| No | Sure |
| No | No |
| No | No |
| No | No |
I put these outcomes right into a desk for example that in every process given to an agent, we now have a number of dimensions of high quality, of issues that we need to “go proper”. Every agent run can “go mistaken” in a single or a number of of those dimensions, and the extra dimensions there are, the much less possible it’s that an agent will get every thing accomplished the way in which we would like it.
Sunk value fallacy
I’ve been questioning – let’s say a group makes use of background brokers for the sort of process, the sorts of duties which might be sort of small, and neither necessary nor pressing. Haiven is an internal-facing utility, and has solely two builders assigned for the time being, so the sort of beauty repair is definitely thought-about low precedence because it takes developer capability away from extra necessary issues. When an agent solely sort of succeeds, however not absolutely – through which conditions would a group discard the pull request, and through which conditions would they make investments the time to get it the final 20% there, although spending capability on this had been deprioritised? It makes me surprise concerning the tail finish of unprioritised effort we would find yourself with.
