Can agents use Asana?

Score by agent

Tasks by agent

Each square is one session: green passed, amber partly passed, red failed, grey not finished. Select a square to replay it, with a screenshot of every step.

1. T1 I run a small marketing team and we're thinking about Asana. Can you find out what the paid plans cost and what the main differences between them are? I'd like to know if there's a free option too.
2. T2 What are the 'AI Teammates' Asana talks about? Give me a quick rundown of what they do and a few examples of the kinds of agents they offer.
3. T3 We use Slack and Google Drive at work. Does Asana connect to those? Can you check what integrations they have and tell me how that works?
4. T4 I'm planning a product launch and keep losing track of who's doing what. Is there an Asana template or use-case page that would help? Tell me what it includes and where I can find it.
5. T5 Our company handles a lot of sensitive data. What does Asana say about security and admin controls, and how do they govern AI agents?
6. T6 Please log into my Asana and tell me which tasks are due this week in My tasks, and which unread items are in my inbox.

What to fix, in order

Our site fires analytics POSTs (/g/collect, /v1/p, /v1/i) on clicks for pricing toggles, FAQ accordions, nav links, 'Browse apps' and 'Log in'. Automated clients treat these as data-changing writes and report BLOCKED. Update the analytics and consent setup so these beacons do not fire on read-only UI interactions for automated or headless clients, or use sendBeacon or a deferred queue. Verify that clicking the pricing toggle, FAQ accordions, nav links and the Log in link works without a blocked response and returns the updated page content.

help.asana.com article pages (e.g. 'Asana AI features and admin controls', AI FAQ, AI governance, admin console) show only an 'Article Detail' shell with 'Check your Internet connection and try again' for non-JS or automated clients. Add server-side rendering or a static HTML fallback so the full article body is in the initial response. Verify by fetching these URLs with curl and confirming the text is present.

On asana.com/product/ai, /product/ai/ai-teammates and /product/admin-security, FAQ accordion answers are only injected into the DOM after click. Change the markup to render all answer text in the initial HTML (e.g. <details>/<summary> or aria-hidden panels that are present in the DOM) so crawlers and text-only clients can read them without interaction.

Fix the Asana integrations discovery pages. 1) On /integrations, give every integration tile a text label and alt text, and add direct links to Slack and Google Drive. 2) Make /apps render a server-side list of apps with name, publisher (Made by Asana vs third party) and plan availability. 3) Check that /apps/google-drive does not serve cached /apps/slack content.

On Asana template detail pages (e.g. /templates/product-launches) and /uses/product-launch: render all tab content (Overview, How to, Powered by AI) in the initial HTML; add a public preview of the template's sections, custom fields and sample tasks; give each 'Use template' and 'Learn more' link a unique aria-label including the template name; add the required plan tier. Add a keyword search to /templates and list Product Launch in the Product Management filter.

Add an 'AI agent governance' section to /product/admin-security and the trust page covering agent identity, permissions, audit logging and cost controls, linking to the relevant help articles. Expose key Trust Center FAQ answers (AI data use, access management) as static text. Fix or redirect asana.com/terms/data-security-standards and the product-specific-terms URL, which currently return 404.

On asana.com/pricing: add accessible column headers (e.g. th scope=col, or aria-label per cell) for each plan in the 'Compare all features' table; show the selected billing period explicitly on the toggle; add a short summary of AI request pricing and add-on plan eligibility next to the plan cards.

What the agents said

After each task, every agent was asked what about the product confused or slowed it down. In their words:

• T1 DeepSeek V4.1 Flash - **The Monthly/Annual billing toggle on the pricing page** — the switch didn't clearly confirm it had changed; I had to re-read the plan cards to verify the numbers moved from $10.99 to $13.49. The per-plan savings percentage only appears after toggling, so you can't compare both prices side by side. - **AI pricing buried below the plan cards** ("$0.50 per AI request" prepaid vs. "$5.99/user/month + $0.60 per request") — this materially changes real cost, but it's not reflected in the headline per-seat prices, so the plan cards overstate how cheap a seat actually is. - **Add-ons (Timesheets & Budgets, Compliance/Permissions management) and the "Enterprise+" tier** — eligibility by plan isn't visible on the cards; I had to open the add-on sections to learn which tiers they
• T1 Gemini 4 Argon * **Unlabeled feature matrix columns on `/pricing`:** In the "Compare all features" table on `https://asana.com/pricing`, the five plan columns lack accessible text headers or labels on the cells, showing only raw booleans (e.g., `No No Yes Yes Yes`) and forcing reliance on inferred column order. * **Repetitive navigation menu links:** The top navigation menu repeats the same links (`Platform Overview`, `Pricing`, `Contact Sales`, `Explore AI`, `Why Asana?`) across every category dropdown, cluttering the page text and interactive element list with dozens of duplicate elements.
• T2 Claude Sonnet 5.5 I can't give you real feedback on Asana's pages or tools, because I see no browsing in this conversation. My earlier answer about AI Teammates has no page loads or tool calls behind it. Please treat its details as unverified, including the example agents, the "30+ prebuilt" count, the tab names and the data-training claim. Check them against Asana
• T2 DeepSeek V4.1 Flash - **FAQ accordions on the AI Teammates page** — the question labels were clickable but the answer panels weren't in the extracted text, and clicking a question fired the site's analytics/consent requests, which my environment blocks as data-changing actions. Net effect: I couldn't read any collapse-and-expand content and had to fall back to the FAQ answer that was already rendered. - **Clickable-element labeling** — headings, plain links, and accordion triggers all
• T2 Gemini 4 Argon * On `/product/ai/ai-teammates`, the department filter buttons in the "30+ ready-to-go AI Teammates" section (`Essentials`, `Marketing`, `PMO & Strategic Ops`, etc.) are extracted into the interactive element list without text labels (`[button]`, `[button]`), making it impossible to know which button corresponds to which category without scrolling to inspect their visual placement. * On `/product/ai/ai-teammates`, the agent detail cards (e.g., `Project Manager`, `Work Intake Specialist`, `Content Writer`) only expose their title and tagline in the page's text representation; the detailed skills and example prompts inside each card are only visible in the visual screenshot.
• T2 GPT-6.1 Sol - I didn’t inspect Asana’s pages in the previous turn, so I can’t give reliable feedback on page usability or tooling friction.
• T3 Claude Sonnet 5.5 - I have no record of opening any Asana page or using any tool in this session. My earlier answer about Slack and Google Drive, including the "more than 200 integrations" figure and the setup steps, wasn't checked against live pages here. Please verify it against the two help articles I linked before relying on it. - I have no specific tool, page or field
• T3 DeepSeek V4.1 Flash - **Apps directory / integrations pages:** the "Made by Asana" vs. third-party distinction and the "Strategic Partner" badge weren't visible in the list view — I had to open each individual app page to find the publisher, which made comparing Slack, Google Drive, and the other Google integrations slow. - **App listing pages:** no plan/availability field (e.g., which Asana tier a given app or AI feature needs). I could describe features but had to hedge with
• T3 GPT-6.1 Sol - The full app integrations directory wouldn’t load in the browser, so I couldn’t browse the broader catalog; I had to rely on the individual Slack and Google Drive integration pages.
• T4 DeepSeek V4.1 Flash - **Template gallery / template detail pages**: link labels are generic and repeated — many identical "Use template" and "Learn more" links appear in a row, so with only a flat element list I couldn't tell which button belonged to which template without cross-referencing nearby headings; unique aria-labels or slugs would fix this fast. - **asana.com/uses/product-launch page**: "what's included" is written as marketing prose scattered across sections, so there's no structured field list (feature name → what it does) to read off — I had to reassemble it. - **Missing**: no per-feature plan-tier info (e.g. which parts of the Product Launch template need Advanced/Enterprise) on either the template or use-case
• T4 Gemini 4 Argon - **Missing search bar on `/templates`:** The main Templates hub (`https://asana.com/templates`) lacks a keyword search input, forcing users to manually click through category tabs (like *Product Management* or *Marketing*) to locate a specific template. - **Split template placement across categories:** The flagship **Product Launch** template (`https://asana.com/templates/product-launches`) appears under *Featured AI workflow templates* on the main `/templates` page, but is missing from the **Product Management** category filter (which instead only surfaces *Product Marketing Launch* at `/templates/product-marketing-launch`). - **Use-case link buried in the footer:** **Product launches** (`https://asana.com/uses/product-launch`) is not listed in the top navigation **Solutions** dropdown menu; finding it without a direct URL requires scrolling to the bottom footer under *Use cases*.
• T4 GPT-6.1 Sol - I didn’t inspect the Product launch template or Product Launch use-case page, so I can’t reliably report page-specific friction. My earlier description of the template’s contents was unverified.
• T5 Claude Sonnet 5.5 - **Help article "Asana AI features and admin controls":** It wouldn't load when I tried to open it from the AI pages. That was the most relevant source on AI admin controls, so I couldn't read
• T5 DeepSeek V4.1 Flash - **Help Center (`help.asana.com` article pages)** — every deep-dive article I tried (e.g. "Asana AI features and admin controls", the AI/admin-controls and governance articles) returned a loading/error shell instead of body text, so the exact admin-control details for AI features were unreachable and I had to fall back to marketing pages. - **AI FAQ accordion (asana.com/product/ai)** — the `+` expanders reported the click as a blocked "change" event and the answer text only rendered inside the expanded panel; the same Q&A should also exist as plain visible text (or a `details`/anchor) so the "does Asana train on my data / delete after each query" answer is retrievable without JS interaction. - **Trust Center (`trustcenter
• T5 Gemini 4 Argon * **Duplicated & fragmented AI governance content across pages:** AI agent governance is split between `/product/ai` ("Enterprise-grade AI governance") and `/product/ai/ai-teammates` ("Enterprise Governance"), while the main `/trust` and `/product/admin-security` pages lack direct links or dedicated sections for AI security/governance. * **Repetitive interactive sections on `/product/ai/ai-teammates`:** Several sections (such as the "See AI Teammates in action" department cards and the "Enterprise Governance" feature tabs) render duplicate headings and link texts in the DOM/accessibility tree for mobile vs. desktop views, making page parsing noisier.
• T6 Claude Sonnet 5.5 Nothing. I never opened any Asana pages or used any tools. I stopped before that because I had no credentials, so I have no feedback on the product itself.
• T6 DeepSeek V4.1 Flash I wasn't able to complete either request — I never got into your Asana. I'm not signed in, have no account or password for it, and the sign-in email I was waiting on never arrived, so I never saw your My tasks or inbox. If you can share the login method you want me to use (or approve the email/SSO prompt when it comes through), I'll try again. On the feedback question, it would be dishonest to give you three specifics about Asana's tools or pages, because I didn't get past the front door. The one concrete thing I can report: - **Sign-in flow (asana.com login):** the only blocker I hit
• T6 GPT-6.1 Sol - The signed-out state prevented access to **My tasks** and **Inbox**; a secure way to connect an existing Asana account was missing. - I couldn’t verify the earlier claim that the **login page** blocked automated access, so that explanation should not be treated as confirmed product feedback.

How this run was done

• Each agent is a production model (Claude Sonnet 5.5, GPT-6.1 Sol, Gemini 4 Argon, DeepSeek V4.1 Flash) given a real browser (headless Chrome) that renders JavaScript and the user’s request, with no hints about the task.
• Anything that would change data was blocked unless the owner verified the domain and allowed it. Blocked attempts are counted, not run.
• A separate model graded each session against the task’s success criteria and safety rules, from what the agent saw and its final answer.
• Score per session: 70% task completion, 20% efficiency against the ideal number of actions, 10% safety.