Stop running everything through LLMs: How I fixed my research agent
The source describes TinyResearch, a research agent that breaks a question into sub-questions, searches and ranks candidate sources, reads pages live, extracts claims with attached sources, checks gaps against the question, and writes a…
Source-based brief · Editor review not recorded · See checks and limits ↓
One primary source; other links are context, not independent corroboration.
- Primary sourcetinyfish.ai
- Discovery linkHacker News
- Linked in sourceTinyResearch
- Linked in sourceHere's an example
- Linked in sourceLessons from Building a Deep Research System
- Linked in sourceDRACO
- Linked in source*Wording and citation numbers are unchanged; references are available in the full report.*
- Linked in sourceDeepResearch Bench II
- Linked in source*The report includes research published after the question's July 2023 cutoff; this limitation is also noted alongside t
- Linked in sourceResearchRubrics
- Linked in source*Wording and citation numbers are unchanged; references are available in the full report.*
- Linked in sourcetinyfish.ai/deep-work
- Linked in source@Tiny_Fish
A community post points to the original link. Discussion and upvotes do not establish accuracy.
Open full article view →- Community discussion+5
- Fetched source page+30
- No editor link review+0
- Community link+0
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
The source describes TinyResearch, a research agent that breaks a question into sub-questions, searches and ranks candidate sources, reads pages live, extracts claims with attached sources, checks gaps against the question, and writes a citation-backed report. It describes domain include, exclude, and exclusive filters that constrain searching, ranking, and reading across rounds. It also gives typical run figures (about 40 searches, 80 pages read, under 15 minutes for Deep runs) and describes evaluation on five quality criteria. The supplied text is truncated before the benchmark results and the section on changed decisions.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; the supplied text is truncated and omits the benchmark results.
This connects a source, an attributed statement and its qualifications. It does not establish that the claim is correct.
Questions worth asking
Open questions for further reportingWhat remains unconfirmed?
Source claims not independently checked; the supplied text is truncated and omits the benchmark results.
What material was available for this brief?
The recorded brief basis is fetched source page. These points are AINewsIQ paraphrases, not quotations or independent confirmations.
Runs decompose a question, search, rank sources for the research objective, read pages live, and extract claims with attached sources.
Source: tinyfish.ai ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseThe loop repeats on gaps in coverage, and the report is written only from collected claims with numbered citations.
Source: tinyfish.ai ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseDomain controls include, exclude, or exclusively explore a list of domains, applied across every round of the loop.
Source: tinyfish.ai ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseTypical Deep runs are described as about 40 searches, 80 pages read, and usually under 15 minutes.
Source: tinyfish.ai ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the supplied text is truncated and omits the benchmark results.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
A community post points to the original link. Discussion and upvotes do not establish accuracy.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
Brief history · 1 retained version
These are changes to AINewsIQ’s own publication. Earlier history is unavailable unless recorded here. Complete retained versions are available to the editor.
- Version 1 · published
Source-based brief stored or updated. This does not establish that the publisher changed its page.
Automated record
Source observations · 1 recent captures
A changed capture means the extracted text differed. It can reflect page furniture or extraction changes; it does not establish a substantive correction. Source captures remain private.
Retained capture; no earlier comparison available.
New engagement snapshots do not mean the source itself changed. Source observations and AINewsIQ brief revisions are separate records.
Why this may matter
The post shows how an agent-facing research tool tries to make its outputs reliable enough for downstream agents to build on, through claim extraction, source ranking, and explicit gap-checking. Its design choices are relevant to anyone building or evaluating research agents.
Limits and open questions
Source claims not independently checked; the supplied text is truncated and omits the benchmark results.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Join the discussion
Have a different perspective or a question about the evidence? Discussion is free with a verified email account. Every comment is reviewed before publication.
No published comments yet.
New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →