Editorial policy and disclosure

Verdicts are independent

Every verdict is written from the tool’s own release notes, docs and (when marked Tested) hands-on use. Money from tool makers cannot buy a better verdict, a higher rank in a “best for” list, or the removal of cons.

Reported vs Tested

• Reported: written from official sources (release notes, README, docs, announcements) that we fetched and linked. We have not run this release ourselves.
• Tested: we ran a small hands-on smoke test (install plus a short task) and describe what happened. Every Tested page states what was run, on which model and hardware, on what date, and what was not covered. A smoke test is not a benchmark or a quality evaluation. Most of our Tested entries used a small local open-weight model (Qwen2.5-3B-Instruct, 4-bit) on a CPU-only Linux machine with no vendor account, so they show that the tool installs and runs, not how it behaves with a vendor’s own hosted models.

Anything we could not confirm is listed under “What we have not verified” on that page.

How “best for” picks are chosen

Ranks are editorial judgement made by Agentic Weekly when an entry is written or updated. They are not benchmark results, user ratings, popularity counts or paid positions.

• We rank only the 139 tools we track, not the whole market. "#1" means top of the tools we cover for that task, not best overall.
• The reason for each rank is the one-line blurb shown beside it. Typical reasons are how well the tool's own docs say it fits the task and how actively it is maintained according to its dated release notes.
• There is no numeric scoring formula, and we have not run quality head-to-head comparisons between ranked tools; our research studies measure install size, startup time and speed for some tools, and those numbers do not set ranks. Where a rank looks like a verdict on quality, it is our reading of official sources, not a measured result.
• The Tested label does not raise a rank. Tested means a small smoke test (install plus a short task, usually on a small local model), not a benchmark. Reported and Tested entries are ranked from the same kind of evidence.
• Payment cannot change a rank. Featured listings are labelled and are never used to order a list.
• Prices and plan details are shown only with a date and an official source. Where we could only find a third-party figure, or could not read the official page, the entry says so.
• Ranks can change when a release, price or doc changes. Each page shows when it was last verified.

Paid placements

Tool makers can pay for a featured listing. Featured entries carry a visible “Featured · Paid placement” label everywhere they appear. Rankings within “best for” pages are editorial and are not ordered by payment.

Affiliate links

Some outbound links are affiliate links (marked rel="sponsored" and labelled on the page). We may earn a commission if you sign up, at no extra cost to you. An affiliate relationship never changes a verdict.

Corrections

Spotted a mistake? Email hello@theagenticweekly.com with a source and we will correct it and update the “last verified” date.

News briefs: speed, labels and corrections

News briefs (/news) are published fast, so they follow stricter rules than a full write-up. Every brief links the vendor’s own source, shows when our watcher first saw the item and when the source published it, and is labelled Reported unless we ran the release and say exactly what was run. A brief states what we have not verified, never adds a verdict the facts do not support, and quotes the source only in short, checked excerpts.

If a brief is wrong we fix it in place, add a dated entry under “Corrections and updates” on that page saying what changed, and move the “Updated” time. If we cannot stand behind a brief we replace its text with a short note and keep the URL. We do not silently rewrite a brief after the fact. We publish a limited number of briefs per day so that each one is checked against its source before it goes live instead of being generated in bulk.