Anthropic — Anthropic's desktop AI coworker for non-coding knowledge work.
cowork agent
Claude Cowork today vs. yesterday?
Anonymous, one click, one vote per agent per day.
Pricing and cadence split Objective evenly — 0.2 of the total each.
Fewer than 3 votes on record → neutral 0.50, shown as provisional rather than as a real reading.
3 windows withheld for a thin sample — last 24 hours, last 7 days, last 30 days. Withheld, not averaged in as a zero.
No window clears the 5-post floor → neutral 0.50, shown as provisional.
2 windows withheld for a thin sample — last 7 days, last 30 days. Withheld, not averaged in as a zero.
Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move.
Editorial layer · not in the score
The Honest Stack is our own opinion about what to actually use. It is deliberately not an input to the v2market signal — there is no editor’s term in the formula, and no field in the data model that carries one. Read it as a second, human opinion beside the number, never as part of it.
Entered at catalog seed — pending verification.
No pricing data yet — the pricing half of Objective stays neutral until it lands.
No pricing changes logged yet.
Daily net of anonymous better/same/worse votes. Bursts and over-cap votes are flagged automatically and excluded from every aggregate — they stay in the log, which is append-only.
No votes yet — cast the first one above.
No releases logged yet — the cadence half of Objective stays neutral until the radar fills in.
Objective, sourced facts about Claude Cowork pulled from the news record. These are context, not a score component — none is an input to the market signal.
lots of people are using artifacts in agents like Claude Code/Cowork
Lots of people are using artifacts in agents like Claude Code/Cowork.
Claude Code/Cowork is an agent.
Television is compatible with Claude Cowork.
The digest · weekly
The most recent events linked to Claude Cowork, so you can read the record behind the number. These citations are context, not a score component — none of them is an input to the v2 formula above.
Anthropic asks Claude users to share voice data for AI model training
Show HN: Television – an open source GUI for your agent harness
Hackers breach OpenAI using Claude tools, gaining access to employee accounts
Anthropic says its model Claude is helping to build the next version of itself
Show HN: MCPJam - the first testing & evaluations platform for MCP servers
Lots of people are using artifacts in agents like Claude Cowork.
Claude Cowork is an agent.
People are using artifacts in agents like Claude Code/Cowork.
Claude Cowork is an agent harness.
Artifacts are used in Claude Cowork.
Claude Cowork does not handle internal hosting when creating custom internal apps/artifacts.
Claude Cowork does not handle RBA (Role-Based Access) when creating custom internal apps/artifacts.
Claude Cowork locks users into a single provider.
Claude Cowork does not allow users to switch models/harnesses anytime.
Claude Cowork does not handle RBA (Role-Based Access) for custom internal apps/artifacts.
Claude Cowork locks users into a single provider and does not allow switching models/harnesses.
Claude Cowork does not handle internal hosting or Role-Based Access (RBA) for custom internal apps or artifacts.
Claude Cowork locks users into a single provider and does not allow switching models or harnesses at any time.
Claude Cowork does not handle internal hosting for custom internal apps/artifacts.
Claude Cowork does not allow users to switch models or harnesses anytime.
Claude Cowork does not handle internal hosting or RBA (Role-Based Access) for creating custom internal apps/artifacts.
Claude Cowork does not handle internal hosting or RBA for creating custom internal apps/artifacts as well as Type.com.
Claude Cowork locks users into a single provider/model/harness.
Claude Cowork is comparable to Codex.
Claude Cowork is not primarily built around collaboration and customization, unlike Ardent.
Claude Cowork is designed to help with knowledge work.
Claude Cowork is an agent.
Claude Cowork is built to help with knowledge work.
Claude Cowork is an agent designed to help with knowledge work for less-technical people outside engineering.
Claude Cowork is designed for less-technical people outside engineering.
Claude Cowork is an agent designed to help with knowledge work.
In Claude Cowork, parameters are written in natural language.
Claude Cowork's interaction model replaces command-line flags and arguments with tools, skills, and context.
In Claude Cowork, the parameters for commands are written in natural language.
Claude Cowork uses an interface that resembles a terminal, with commands structured as '/skill-name [param1] [param2]'.
Users of Claude Cowork need to know the existing capabilities and how to invoke them.
Claude Cowork's interface uses a format similar to '/skill-name [param1] [param2]'.
The parameters for Claude Cowork are written in natural language.
Claude Cowork's interface uses a syntax that involves /skill-name [param1] [param2].
The parameters in Claude Cowork's interface are written in natural language.
Claude Cowork utilizes an interface that looks terminal-like, featuring commands structured as /skill-name [param1] [param2].
Claude Cowork's interface uses a format like "/skill-name [param1] [param2]".
Users of Claude Cowork need to know how to invoke its capabilities.
Users of Claude Cowork need to know the capabilities that exist.
Parameters in Claude Cowork are written in natural language.
Claude Cowork tools look terminal-like.
Claude Cowork uses the format /skill-name [param1] [param2].
The parameters in Claude Cowork are written in natural language.
Subjective claims voiced about Claude Cowork, each tagged with its polarity and linked to where it was said. Opinions from the record — never folded into the number.
Claude Cowork locks users into a single provider.
Type.com claims that Claude Cowork is inferior to Type.com for certain use cases, specifically by locking users into a single provider and not handling internal hosting or RBA for creating custom internal apps/artifacts.
Creating a custom internal app/artifact is less effective with Claude Cowork because Type.com handles internal hosting and RBA better.
Claude Cowork may lock users into a single provider.
Claude Cowork is not as good for creating custom internal apps/artifacts or handling internal hosting and RBA compared to type.com.
Claude Cowork is not as good as Type.com for creating custom internal apps/artifacts.
Claude Cowork is less suitable for creating custom internal apps or artifacts compared to Type.com, which handles internal hosting and RBA.
Claude Cowork does not handle internal hosting or Role-Based Access (RBA) as effectively as Type.com for creating custom internal apps/artifacts.
With Claude Cowork, the user still needs to know the capabilities that exist, and how to invoke them.
With Claude Cowork, the user still needs to know the capabilities that exist and how to invoke them.
The interaction with tools like Claude Cowork requires the user to know the capabilities that exist and how to invoke them, which is presented as a limitation.
Claude Cowork's interface still looks surprisingly terminal-like.
With Claude Cowork, the user still needs to know the capabilities that exist and how to invoke it.
Claude Cowork still looks surprisingly terminal-like.
Tools like Claude Cowork still look surprisingly terminal-like.