# askround changelog — Alegauss

Every entry in askround's roadkeep ledger, dated by the commit that wrote it.

- 2026-11-12 · AR43: The site is not built to be read by assistants, and askround never measures whether they name askround itself
- 2026-11-12 · AR42: There are no docs pages: install, a first session in Claude Code, the MCP tools and the CLI reference live nowhere
- 2026-11-12 · AR41: Nothing builds and deploys the site when it changes
- 2026-11-12 · AR40: askround has no public site: nowhere to see what a round reports, install it or read the docs
- 2026-11-12 · AR38: askround is not wired into a project the way roadkeep is: one install that every clone and every surface gets
- 2026-11-12 · AR37: Nothing measures how many tokens each MCP response costs the agent, so outputs grow unnoticed
- 2026-11-12 · AR36: An agent asking the same question again the same day pays for the same round twice
- 2026-11-12 · AR35: A round takes minutes of searched calls, longer than an MCP call should block the agent
- 2026-11-12 · AR34: An agent could spend the user's API money on rounds without the user ever agreeing to the amount
- 2026-11-12 · AR33: A bad round is discovered after it is paid for: a leading question, personal data or a cost over budget
- 2026-11-12 · AR32: Output is meant for a person to read, with no stable schema an agent or a script can rely on
- 2026-11-12 · AR31: A round hands the agent every raw answer, so one check of a product spends tens of thousands of tokens of context
- 2026-11-12 · AR30: No written laws bind askround's design, so the agent-first rules can erode one feature at a time
- 2026-11-12 · AR29: Tests would call live APIs, costing money and breaking on every provider change
- 2026-11-12 · AR27: No Claude Code skill tells an agent when to use askround instead of asking the user to test a prompt
- 2026-11-12 · AR26: Disagreements between assistants on a fact, such as a model's licence, are not flagged for a check at the source
- 2026-11-12 · AR25: Researching a question across assistants means reading each answer and merging the sources by hand
- 2026-11-12 · AR24: An agent in Claude Code cannot ask other assistants mid-analysis; it has to stop and ask the user
- 2026-11-12 · AR23: A round cannot be exported to a dashboard or another project's data
- 2026-11-12 · AR22: The cost of a round is unknown before it runs, and web search is billed apart from tokens
- 2026-11-12 · AR21: Nothing compares a round with the previous one: a new rival, a rank lost, a product dropped
- 2026-11-12 · AR20: Rounds are not kept as a series, so a product entering or leaving the answers goes unnoticed
- 2026-11-12 · AR19: A question could carry personal data, an email or a person's name, to every provider at once
- 2026-11-12 · AR18: Nothing warns when a question names the product it tests, which makes its answer worthless
- 2026-11-12 · AR17: Finding which question leads an assistant to a product took four manual tries
- 2026-11-12 · AR16: Questions live in chat history; there is no prompt set per product to run again next week
- 2026-11-12 · AR15: Claims about the product are not checked against what is true, so a wrong 'needs NVIDIA' goes unnoticed
- 2026-11-12 · AR14: A cited link or picture may belong to another product, like a Store page of a different app shown for Modelado
- 2026-11-12 · AR13: A product an answer names may not exist, like two Windows apps no search could find
- 2026-11-12 · AR12: There is no short report of a round; reading it means opening every raw answer
- 2026-11-12 · AR11: What an answer claims about the product is not captured, such as 'CPU only: Check build' in a table
- 2026-11-12 · AR10: The links an answer cites are not collected, so which page brought the product (site, repo, store) is unknown
- 2026-11-12 · AR9: The rivals an answer recommends are not listed, so a competitor like Modly is found only by reading
- 2026-11-12 · AR8: Whether a product is named, and in which position, is read by eye in each answer
- 2026-11-12 · AR7: A rate limit, timeout or provider error aborts the round instead of being retried and reported
- 2026-11-12 · AR6: A question cannot be asked as someone in a given country and language would ask it
- 2026-11-12 · AR5: The model, tools and settings behind an answer are not recorded, so a change cannot be told from drift
- 2026-11-12 · AR4: One answer is taken as the answer, though the same question gives a different list on the next run
- 2026-11-12 · AR3: Which providers can run depends on keys in the environment, and nothing says which ones are there
- 2026-11-12 · AR2: Providers are called without web search, so an answer cannot name a product newer than the model's training
- 2026-11-12 · AR1: No code exists to send one question to several assistants and keep their answers side by side
- undated · AR39: Running askround would mean installing provider SDKs and their dependency trees
- undated · AR28: askround cannot be installed: there is no package, no release and no README first screen