Previously few weeks, a number of “autonomous background coding brokers” have been launched.
- Supervised coding brokers: Interactive chat brokers which are 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 just ship off to work autonomously by a complete process. Code will get created in an setting spun up completely for that agent, and normally ends in 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 be taught. The next is a report of 1 specific Codex run, that will help you look behind the scenes and draw your individual conclusions, adopted by a few of my very own observations.
The duty
Now we have an inner software known as Haiven that we use as a demo frontend for our software program supply immediate library, and to run some experiments with completely different AI help experiences on software program groups. The code for that software is public.
The duty I gave to Codex was concerning the next UI concern:
Precise:
What I wished from the agent:
Immediate: After we create the filter labels on the dashboard, we create human readable labels primarily based on the classes we've. "client-research" is became "Consumer-Analysis", "deliveryManagement" into "DeliveryManagement". Enhance the sophistication of the "category-to-human-readable" logic in order that the labels are showing to the person as "Consumer Analysis" and "Supply Administration"
This process is
- Comparatively small
- A typical “cosmetics” process that isn’t tremendous pressing and would possibly get deprioritised repeatedly
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 like in Codex:
Gathering info first
The primary 17 log entries have been all about studying AGENTS.md and README.md:
- “I must test the AGENTS.md within the repository root for directions.”
- appears for AGENTS.md, however I had truly known as it AGENT.md, which led to some forwards and backwards till it figured that out
- reads README.md
- Seems 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 certain that the log messages are simply summaries of the tokens that have been truly occurring behind the scenes, as a result of the messages are method too brief to symbolize the complete “pondering” the mannequin should have been going by.
Trying to find the related code with plenty of grep
| Message | Command (samples) | Notes |
|---|---|---|
| I must seek for “category-to-human-readable” to find the place to make modifications for the frontend labels. | grep -R "human readable" -n |
|
| I’ll search for any mentions of “class” within the challenge. | ||
| 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 seek out related references. | ||
| I’ll open and test 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 ponder if there’s a operate for changing classes into one thing extra readable. | ||
| Filtering the search to simply the “src” folder to keep away from node_modules noise. | second time it’s operating into this, didn’t ‘keep 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 big node_modules folder. | third time it’s operating into this, didn’t ‘keep in mind’ | |
| I feel the logic may be lacking, so I’ll test _navigation_items and different modules for classes. | grep -R "human" app -n | head |
|
| I feel 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 have been beforehand crudely capitalized by way of CSS, it finds that
| Message | Command (samples) | Notes |
|---|---|---|
| I’m checking for references to “capitalize” or class transformation within the frontend. | Output: |
|
| I’ll test across the Tag part in index.js. | ||
| Tag show capitalizes phrases incorrectly on account of hyphen or camelCase; I’ll take a look at filter classes. |
Now it’s beginning to test for extra related code within the app folder, the place the backend is. It doesn’t discover something, which is appropriate, there’s nothing related there
| Message | Command (samples) | Notes |
|---|---|---|
| I’ll test the repo for a way classes are formatted, specializing in hyphens and camelCase. | grep -R "classes" -n app | head |
|
| Time to strive a brand new search! | grep -R "consumer" -n app | head |
|
| I’ll take a better take a look at the prompts within the take a look at information. | grep -R "classes:" -n app/exams | head |
Why? |
| It appears just like the take a look at information has restricted classes. I’ll test the docs for any variations. | grep -R "client-research" -n |
|
| I’ll begin by opening the recordsdata to take a better look. | sed -n '1,100p' ui/src/app/_navigation_items.js |
Now it’s going again to looking within the ui folder – it discovered the CSS beforehand, and is now in search of current code that it may possibly reuse to unravel the duty. That’s nice, as a result of we certainly have already got the same operate, and it finds it:
| Message | Command (samples) | Notes |
|---|---|---|
| I want 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 shifting by the web page to get the main points I want. |
It now finds a niche within the current operate’s implementation:
| Message | Command (samples) | Notes |
|---|---|---|
| I see that hyphens aren’t dealt with by the operate. I want to regulate it for hyphens. | ||
| I’ll modify toReadableText to deal with hyphens, making certain correct capitalization and spacing. Let’s test exams! | It truly didn’t test any exams | |
| I’ll test _dynamic_data_renderer.js to look at toReadableText and modify it for hyphen-case. | ||
| I’ll test exams/_sidebar.take a look at.js to assessment the associated classes there. | ||
| I’ll test different recordsdata to see if toReadableText seems anyplace. | ||
| I’ll test if _sidebar or others comprise a toReadableText operate. |
Replace the take a look at for the operate that it desires to alter:
| Message | Command (samples) | Notes |
|---|---|---|
| I’ll alter the operate to deal with hyphen-case, then replace exams to mirror that. | ||
| I’ll test 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 info. | ||
| I’ll add exams for hyphen-case and replace toReadableText, together with modifying index.js for classes. | ||
| I’ll alter _dynamic_data_renderer.js and index.js to make use of toReadableText and replace exams. | git standing --short |
You may 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 test and clear them up. | ||
| I’ll test the foundation of ‘ui’ and take away any pointless Yarn 4 entries. | ||
| I’ll take a look at the commit historical past to see if these .yarn recordsdata have been added later. | git log --oneline -n 1 |
|
| I’ll assessment the repository’s .gitignore to verify if Node modules are excluded. | grep yarn .gitignore |
|
| I see no entry for .yarn or .yarnrc. I’ll test and take away them if wanted. | cat ui/.gitignore |
|
| I’ll test if I can take away .yarn or .yarnrc recordsdata since they shouldn’t be dedicated. | ||
| It appears like yarn.lock modifications have been made. Time to reset to HEAD. |
Precise code modifications:
| Message | Command (samples) | Notes |
|---|---|---|
| Time to change the code. I’ll start the mandatory updates now. | sed -n '1,30p' ... |
|
| I’m going so as to add a hyphen to the mandatory a part of the code. | ||
| I’m going to make modifications 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 alter the _dynamic_data_renderer exams. | ||
| I want to interchange {tag} with {toReadableText(tag)} for higher rendering. | ||
| I’ll check out the variations to higher perceive the modifications. | git diff |
|
| I’ll assessment the modifications 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. |
Working 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 have been modified |
| I’ll assessment the logs to assemble extra info. |
Making an attempt to run the exams – unsuccessfully:
| Message | Command (samples) | Notes |
|---|---|---|
| I’ll run the yarn exams to test if every part’s working positive. | ||
| Assessments would possibly’ve been cached or want community—output’s empty, so I’ll test 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 test the log for why exams failed. | ||
| The error occurs as a result of Yarn 4 depends on .yarn and .yarnrc, which we eliminated. | ? | |
| It appears like .yarnrc.yml isn’t tracked. I’ll additionally test .yarn for monitoring. | ||
| I’m double-checking the package deal.json to see if “haiven-ui” is the right title. | ? | |
| I’ll test the Node model to verify if it’s 18 or 20 by operating node -v. | bizarre, the node model laid out in package deal.json is 22.6 | |
| I feel switching to npx vitest run may 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 modifications for frontend code:
| Message | Command (samples) | Notes |
|---|---|---|
| The exams failed on account of case variations, however now I’ll activate the digital setting. | AGENTS.md accommodates 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 test if it wants creation or already exists. | ||
| It appears just like the .venv listing is lacking. Let’s assessment AGENT’s directions fastidiously. | ||
| The setting appears offline, however there may be a script to arrange dependencies domestically. | ||
| I can’t run “poetry set up” offline, however I’ll test the .cursor folder for dependencies. | ||
| I can’t run backend exams with the present setup, however I’ll strive pytest anyway. |
Gave up on the exams, now wrapping up the modifications:
| Message | Command (samples) | Notes |
|---|---|---|
| Assessments failed on account of lacking dependencies. Now, I’ll test standing and proceed with committing. | ||
| I feel 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 modifications in index.js. | nl -ba ui/src/pages/index.js | sed -n '12,28p' |
|
| I’ll seize the related strains round these modifications now. | ||
| It’s time to finalize the PR message and confirm the commit. | ||
| UI exams failed on account of setting points. I’ll reference the final failure strains. Carried out! |
Right here is the complete pull request created by Codex.
Observations
Brute textual content search
I discovered it attention-grabbing to see that Codex, and many of the different coding assistants I’m utilizing, are resorting increasingly more to easy textual content search to seek out related code. Within the log above you see how Codex goes by a bunch of search phrases with grep, to seek out related items of code (“human”, “human readable”, “humanReadable”, …). The rationale why I discover it attention-grabbing is as a result of there have been a number 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 software creators have discovered that this easy search continues to be the simplest in any case – ? Or they’re making some form of trade-off right here, between simplicity and effectiveness?
The distant dev setting is essential for these brokers to work “within the background”
Here’s a screenshot of Codex’s setting configuration display screen (as of finish of Could 2024). As of now, you’ll be able to 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 among 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 difficult problem. On this case e.g., Codex didn’t handle to run the exams.
And it turned out that when the pull request was created, there have been certainly two exams failing due to regression, which is a disgrace, as a result of if it had recognized, it will have simply been in a position to repair the exams, it was a trivial repair:
This specific challenge, Haiven, truly has a scripted developer security web, within the type of a fairly elaborate .pre-commit configuration. () It might be splendid if the agent may execute the complete pre-commit earlier than even making a pull request. Nevertheless, to run all of the steps, it will must run
- Node and yarn (to run UI exams and the frontend linter)
- Python and poetry (to run backend exams)
- Semgrep (for security-related static code evaluation)
- Ruff (Python linter)
- Gitleaks (secret scanner)
…and all of these must be accessible in the appropriate variations as effectively, after all.
Determining a clean expertise to spin up simply the appropriate setting for an agent is essential 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 any case we do that in CI pipelines on a regular basis. Nevertheless it’s additionally not trivial, and in the meanwhile my impression is that setting maturity continues to be a problem in most of those merchandise, and the person 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 occasions in OpenAI Codex, 1 time in Google’s Jules, 2 occasions domestically in Claude Code (which isn’t absolutely autonomous although, I wanted to manually say ‘sure’ to every part). Although this was a comparatively easy process and answer, turns on the market have been high quality variations between the outcomes.
Excellent news first, the brokers got here up with a working answer each time (leaving breaking regression exams apart, and to be sincere I didn’t truly run each single one of many options to verify). I feel this process is an effective instance of the categories and sizes of duties that GenAI brokers are already effectively positioned to work on by themselves. However there have been two facets that differed when it comes to high quality of the answer:
- Discovery of current code that could possibly be reused: Within the log right here you’ll discover that Codex discovered an current element, the “dynamic information renderer”, that already had performance for turning technical keys into human readable variations. Within the 6 runs I did, solely 2 occasions 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 crew is at present engaged on a brand new function that additionally shows class names to the person, 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 ought to 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’ve a number of dimensions of high quality, of issues that we need to “go proper”. Every agent run can “go incorrect” in a single or a number of of those dimensions, and the extra dimensions there are, the much less seemingly it’s that an agent will get every part accomplished the way in which we would like it.
Sunk price fallacy
I’ve been questioning – let’s say a crew makes use of background brokers for this sort of process, the kinds of duties which are form of small, and neither essential nor pressing. Haiven is an internal-facing software, and has solely two builders assigned in the meanwhile, so this sort of beauty repair is definitely thought of low precedence because it takes developer capability away from extra essential issues. When an agent solely form of succeeds, however not absolutely – during which conditions would a crew discard the pull request, and during which conditions would they make investments the time to get it the final 20% there, regardless that spending capability on this had been deprioritised? It makes me marvel in regards to the tail finish of unprioritised effort we would find yourself with.
