25 Sept 2026
Will social media survive the AI change? What the evidence says
Our overnight sample had no social referrers, while Meta's crawlers made 5.9% of page requests. Usage, labelling rules and the EU AI Act…
A single 0–100 quality score for an AI agent in production, recalculated daily from outcome, reliability, cost, speed and safety, with the sessions behind it — a feature of Latitude’s agent monitoring, in early access.
Agent Score is a feature of Latitude, an open-source platform for monitoring AI agents, announced in Latitude’s changelog on 23 September 2026 and listed on Product Hunt the same day. It gives each production agent one score from 0 to 100, recalculated every day over a rolling window, built from five weighted parts: outcome (35 per cent), reliability (25), cost (15), speed (15) and safety (10). The score links back to the production sessions and the causes that moved it, and can be read through Latitude’s API, SDKs and command line, so a team can put it in a dashboard or a release gate. It is in early access, switched on per organisation, and is not mentioned on Latitude’s pricing page; Latitude itself is free on its Starter plan with 20,000 credits a month, $99 a month on Pro with 100,000, and custom for enterprises. A single number is useful for spotting a regression, and less useful for comparing two different agents, because the weights are Latitude’s choice; a buyer should check whether the weights can be changed to match what matters in their own use. It is listed as “Latitude Agent Score” because “AgentScore” is also the name of an unrelated company that builds payment and compliance infrastructure for AI agents.
An earned signal from verification, reviews, awards, transparency and engagement — the vendor can't buy it.
Updated 9/25/2026
Used it? Your experience helps other buyers decide.
Write a reviewNo questions yet. Be the first to ask about Latitude Agent Score.
Everything here links back to the same verified catalogue. Pick your next stop.