What askround shipped.
Every entry in docs/CHANGELOG.md, read at b39ba6f and dated by the commit that wrote it.
- AR43 · d8e135cThe site is not built to be read by assistants, and askround never measures whether they name askround itself
The site ships a checked llms.txt and JSON-LD, and shows askround's own dated round: named by no assistant yet.
- AR42 · 3205896There are no docs pages: install, a first session in Claude Code, the MCP tools and the CLI reference live nowhere
site/docs builds the docs at /askround/docs/, its MCP and CLI reference generated from the package.
- AR41 · ad343d5Nothing builds and deploys the site when it changes
site.yml deploys the site to Pages; alegauss.github.io/askround/, its docs and llms.txt answer 200.
- AR40 · 6e4b939askround has no public site: nowhere to see what a round reports, install it or read the docs
site/ prerenders the page at /askround/ with a real recorded round; Lighthouse scores 100.
- AR38 · 32beff6askround is not wired into a project the way roadkeep is: one install that every clone and every surface gets
The plugin, askround install and a vendored copy for the web wire every clone.
- AR37 · 647a056Nothing measures how many tokens each MCP response costs the agent, so outputs grow unnoticed
Every MCP tool's response is counted on the recorded rounds against a budget in budgets/mcp-tokens.json, and askround_run returns one brief per question.
- AR36 · 7d06a8cAn agent asking the same question again the same day pays for the same round twice
A question asked again the same way within the day returns the stored round with its age and calls no provider; --fresh asks anew, and a round with failures is asked again.
- AR35 · bf4c5d6A round takes minutes of searched calls, longer than an MCP call should block the agent
With background: true a round or set starts as a job and returns at once with its estimate; askround_job reads its progress and result, and each answer is kept as it lands.
- AR34 · 296d9fcAn agent could spend the user's API money on rounds without the user ever agreeing to the amount
The person sets a day and month budget in a config no tool writes; a run past it is refused before any call as an approval request, and spending comes with every paid result.
- AR33 · f24f009A bad round is discovered after it is paid for: a leading question, personal data or a cost over budget
Every pre-call check runs first and a refusal lists all problems with a code and its fix; askround explain covers each code, and MCP schemas carry the limits.
- AR32 · 04c6e61Output is meant for a person to read, with no stable schema an agent or a script can rely on
Every command's JSON names a versioned schema published in schema/ and validated in tests; each fact carries its answer id and passage range; exit codes are documented.
- AR31 · 760b955A round hands the agent every raw answer, so one check of a product spends tens of thousands of tokens of context
Agents get a brief: a round in a few hundred tokens with answer ids on every fact; askround_answer returns one answer or just the passage around a quote.
- AR30 · 6607611No written laws bind askround's design, so the agent-first rules can erode one feature at a time
askround's six laws open IMPROVEMENTS.md as §0.1, from context is cost to the person sets the money, and the project skill says a rationale names the law it serves.
- AR29 · d011e62Tests would call live APIs, costing money and breaking on every provider change
The suite runs with no key and fails any network call; adapters are tested on a recorded live round, and ASKROUND_LIVE=1 runs each keyed adapter against its API.
- AR27 · 47048f4No Claude Code skill tells an agent when to use askround instead of asking the user to test a prompt
A skill tells an agent when to run askround itself (visibility, discovery, research), how to ask neutrally and within budget; a validated plugin installs it with the MCP server.
- AR26 · 412d3b7Disagreements between assistants on a fact, such as a model's licence, are not flagged for a check at the source
Research mode reports where the assistants disagree on a fact first, with both sides, their passages and the primary sources to settle it; one provider's own sources are not read.
- AR25 · 6f711a3Researching a question across assistants means reading each answer and merging the sources by hand
askround research asks every provider with search, merges the answers' verified statements into claims ranked by provider support, with passages and sources primary first; also an MCP tool.
- AR24 · dc20d1cAn agent in Claude Code cannot ask other assistants mid-analysis; it has to stop and ask the user
askround mcp serves ask, answer, run, report, diff and doctor over stdio with every refusal and the cost cap; a stdio client asked two providers and read an answer.
- AR23 · c2fb2edA round cannot be exported to a dashboard or another project's data
askround export writes a product's rows from the series per day, provider and question as CSV, JSON or a daily.json shape, and the README shows a weekly schedule on Windows and cron.
- AR22 · a4f3f48The cost of a round is unknown before it runs, and web search is billed apart from tokens
A run prints its estimate from a dated price table, refuses one above --max-cost before any call, and reports the actual cost per provider from each API's usage.
- AR21 · dc8fe96Nothing compares a round with the previous one: a new rival, a rank lost, a product dropped
askround diff compares two rounds or set runs per question and provider, naming share and rank changes, rivals and cited pages that appeared or left, and claims made or dropped.
- AR20 · 78d9113Rounds are not kept as a series, so a product entering or leaving the answers goes unnoticed
Every saved round appends a row per answer to series.jsonl, rebuildable from the rounds; askround series gives a product's share per week, day or month per provider.
- AR19 · 859982cA question could carry personal data, an email or a person's name, to every provider at once
Every question, seed, variant and lookup is scanned for emails, phones, CPFs, IPs, API keys and the person's private names, and stops before any call naming what it found.
- AR18 · 6b972a6Nothing warns when a question names the product it tests, which makes its answer worthless
A question naming the product, an alias, a place or a listed phrase is refused before any call; a brand question (--brand, brand = true) runs, marked and reported apart.
- AR17 · cc82580Finding which question leads an assistant to a product took four manual tries
askround discover writes variants of a seed that never name the product, runs them and ranks them by rank and frequency; a 1-run live test ranked the seed first.
- AR16 · a75b9f9Questions live in chat history; there is no prompt set per product to run again next week
A product file's [[question]] entries form a prompt set; askround run asks them all as one set with a question-by-provider table, and examples/modelado.toml holds the four 12/11 questions.
- AR15 · b32ac56Claims about the product are not checked against what is true, so a wrong 'needs NVIDIA' goes unnoticed
A product file holds a product's facts and pages; with --extract the answers' claims are judged against them, and a contradicted or doubted fact is reported with the page that should say it.
- AR14 · a216930A cited link or picture may belong to another product, like a Store page of a different app shown for Modelado
--check-links follows each link and image an answer gives beside a product and flags those landing on another product's page or broken; Modelado's real Store, site and repo pass.
- AR13 · a3d2c31A product an answer names may not exist, like two Windows apps no search could find
askround lookup and --check-rivals check a rival on GitHub, then a searched call; both 12/11 'invented' names exist (design superseded: they exist).
- AR12 · 133a5cbThere is no short report of a round; reading it means opening every raw answer
askround report turns a stored round (the latest by default) into one Markdown or JSON report: frequency and ranks per provider, claims, cited pages and rivals, without the answers' text.
- AR11 · 22e6df6What an answer claims about the product is not captured, such as 'CPU only: Check build' in a table
With --extract each answer's claims about every product (table cells and prose) are read as attribute and value with a verified quote, and a product's claims are aggregated per provider.
- AR10 · 8eb6517The links an answer cites are not collected, so which page brought the product (site, repo, store) is unknown
Each answer's cited pages are normalised; given its domains, a product's cited pages are counted per provider by kind, and third-party domains and rivals' pages are counted too.
- AR9 · 29d139cThe rivals an answer recommends are not listed, so a competitor like Modly is found only by reading
With --extract a round lists every rival the answers recommend, with answer counts, ranks, providers and a quote; on 12/11 Modly led, but a live round today ranks it lower.
- AR8 · 4d5805dWhether a product is named, and in which position, is read by eye in each answer
--extract lists each answer's recommendations in order with quotes, checked against its text, so a product ranks by "Best fit" or prose; live and synthetic answers checked, 12/11 originals not kept.
- AR7 · f9777a8A rate limit, timeout or provider error aborts the round instead of being retried and reported
Rate limits, server errors and timeouts are retried with backoff and Retry-After; a call that still fails is recorded with its attempts and the round finishes, listing failures.
- AR6 · 29d9738A question cannot be asked as someone in a given country and language would ask it
--locale COUNTRY:LANG asks each provider as that locale through its search settings, records what its API ignored, and repeated locales are compared side by side.
- AR5 · be499daThe model, tools and settings behind an answer are not recorded, so a change cannot be told from drift
Every answer records the requested and served model id, search tool, temperature, locale, settings, run and time; --model pins a model and frequency groups by served model.
- AR4 · 20b6ab1One answer is taken as the answer, though the same question gives a different list on the next run
A round asks each provider three times by default (--runs) and --product reports per provider the share of runs naming it and its position in each, raw answers kept.
- AR3 · 9f822bfWhich providers can run depends on keys in the environment, and nothing says which ones are there
askround doctor lists each provider's key variable (never its value), model, search tool and a free check call, telling rejected keys from missing models.
- AR2 · c5ce2a8Providers are called without web search, so an answer cannot name a product newer than the model's training
Every adapter searches with its provider's own tool and keeps queries and cited sources, with --no-search to compare; OpenAI and Gemini were checked live.
- AR1 · f47df19No code exists to send one question to several assistants and keep their answers side by side
askround ask sends one question to every provider with a key (OpenAI, Gemini, Anthropic) in parallel, prints the answers together and saves each raw response with the date.
- AR39Running askround would mean installing provider SDKs and their dependency trees
askround installs alone and imports only the standard library.
- AR28askround cannot be installed: there is no package, no release and no README first screen
The wheel and sdist build, pass twine check and install with no dependencies in a fresh venv; the README opens with the problem and a real round.