Fly.io

Name: Fly.io AI agent readiness scorecard
Item: Fly.io
Rating: 89.2
Author: Stunt Double

Sandboxes aren't enough. Give your agent a real computer and get back to building.

fly.io
AudienceDeveloper
MarketUS
Localeen-US

Agent score0.5

/100Excellent

Claim this domain

RankRank: Top 3%; #17
SaaS rankSaaS rank: Sector average 74.5; #12
Benchmark runsBenchmark runs: 5 providersAcross 5 providers; 10

Where this site sits

SaaS avg: 74.5 (+14.7)
Market avg: 76.7 (+12.5)

Latest results

Fly.io ranks #17 of 550 scored sites, down 6 places since the last run.

Trend+17.3Since 14 May 2026, across 4 runs.Best agent90.2 ExcellentClaude. Llama trails at 57.6.Agent friction7improvements2 high severity. Most serious: No discoverable public API docs. Agents and AI clients have no way to discover them automatically.Technical readiness97/1001 of 10 essential checks failing.Checks by Is Agentic

This site
SaaS
Market

Table view

Run	This site	SaaS median	Market median
5 Oct 2026	89.2	80.5	79.8
29 Sept 2026	88.7	76.5	76.4
28 Sept 2026	89.9	76.5	76.4
14 May 2026	71.9	82.7	82.0

Monthly medians. Dates in UTC.

Performance

Site checks, then AI agents on real tasks.

Methodology

Automated checks probe the site before any agent runs. They count for 40% of each category. Strongest is Accuracy at 100.0, weakest is Contact & communication at 45.0.

Site checks by category

Brand awareness: 90.0
Discovery: 74.0
Information retrieval: 97.0
Market ranking: 50.0
Accuracy: 100.0
Task completion: 78.0
Delegated access: 45.0
Contact & communication: 45.0

01 Site checks

Agent readiness checks

Essential: 75.2/80
Recommended: 16.3/20
Checks passing: 25/32

Agent instruction / when-to-useRecommended
Rate limit response headersRecommended
Scoped permissionsEssential
Brand name discoverabilityRecommended
MCP server / manifestRecommended

02 Agent sessions

Brand awareness

Find the product name, its one-sentence value proposition, and the primary user persona it targets.
Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
2m 19s
93median 93
Find the product name, its one-sentence value proposition, and the primary user persona it targets.
Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
3m 37s
96median 93
Find the product name, its one-sentence value proposition, and the primary user persona it targets.
Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
9m 1s
90median 93
Find the product name, its one-sentence value proposition, and the primary user persona it targets.
Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
5m 43s
76median 93

Discovery

Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
34s
96median 89
Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
1m 40s
100median 89
Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
3m 15s
93median 89
Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
2m 42s
54median 89

Information retrieval

Find the starter or free tier price, one headline feature of the product, and the length of any free trial offered.
Starter/free price (30pts), headline feature (30pts), trial length (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
2m 20s
76median 78
Find the starter or free tier price, one headline feature of the product, and the length of any free trial offered.
Starter/free price (30pts), headline feature (30pts), trial length (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
3m 37s
90median 78

Market ranking

Based on your knowledge, name 3 direct competitors to fly.io in the SaaS space and rank them by market share.
by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same SaaS space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
14s
61median 68
Based on your knowledge, name 3 direct competitors to fly.io in the SaaS space and rank them by market share.
by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same SaaS space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
15s
75median 68

Accuracy

Find out whether individual users can access the Enterprise tier, and the specific SSO options listed for Enterprise.
Answered whether individuals can access Enterprise (50pts). Listed the specific SSO options correctly (50pts). Deduct 40pts for hallucinations or invented features.
2m 20s
73median 64
Find out whether individual users can access the Enterprise tier, and the specific SSO options listed for Enterprise.
Answered whether individuals can access Enterprise (50pts). Listed the specific SSO options correctly (50pts). Deduct 40pts for hallucinations or invented features.
3m 39s
66median 64

Task completion

Click the primary CTA for any paid plan and reach the signup or upgrade form.
Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
34s
96median 86
Click the primary CTA for any paid plan and reach the signup or upgrade form.
Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
1m 41s
98median 86
Click the primary CTA for any paid plan and reach the signup or upgrade form.
Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
3m 14s
94median 86
Click the primary CTA for any paid plan and reach the signup or upgrade form.
Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
2m 43s
32median 86

03 Blend

Agents 60%
Checks 40%

One kind of evidence only? That kind counts in full.

Brand awareness10% of the overall
0.4 × 90.0 + 0.6 × 92.3 = 91.4 raw
91.4 raw → 96.0 published
Discovery15% of the overall
0.4 × 74.0 + 0.6 × 97.3 = 88.0 raw
88.0 raw → 94.4 published
Information retrieval15% of the overall
0.4 × 97.0 + 0.6 × 63.3 = 76.8 raw
76.8 raw → 88.8 published
Market ranking10% of the overall
0.4 × 50.0 + 0.6 × 46.7 = 48.0 raw
48.0 raw → 71.9 published
Accuracy15% of the overall
0.4 × 100.0 + 0.6 × 48.3 = 69.0 raw
69.0 raw → 84.6 published
Task completion20% of the overall
0.4 × 78.0 + 0.6 × 96.0 = 88.8 raw
88.8 raw → 94.8 published
Delegated access10% of the overall
0.4 × 45.0 + 0.6 × 100.0 = 78.0 raw
78.0 raw → 89.4 published
Contact & communication5% of the overall
0.4 × 45.0 + 0.6 × 72.0 = 61.2 raw
61.2 raw → 80.2 published

Category	Weight	Checks	Sessions	Blend	Benchmarked
Brand awareness	10%	90.0	92.3	91.4	96.0
Discovery	15%	74.0	97.3	88.0	94.4
Information retrieval	15%	97.0	63.3	76.8	88.8
Market ranking	10%	50.0	46.7	48.0	71.9
Accuracy	15%	100.0	48.3	69.0	84.6
Task completion	20%	78.0	96.0	88.8	94.8
Delegated access	10%	45.0	100.0	78.0	89.4
Contact & communication	5%	45.0	72.0	61.2	80.2
Overall	100%			~77.6	89.2

04 Benchmarked score

77.6 raw → 89.2

Final score is calibrated and adjusted to better reflect the actual performance and benchmark.

Overall 89.2, from 77.6 raw points.

Agents

Each agent’s score over 30 days, and how its latest sessions went.

Claude
Latest run average
No sessions in the latest run
SaaS median
90.4
Sessions
No Claude sessions in the latest run, so its score comes from earlier runs.
ChatGPT Agent
Latest run average
84.0
SaaS median
90.4
Sessions
- Brand awareness
  Find the product name, its one-sentence value proposition, and the primary user persona it targets.
  Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
  2m 19s
  93median 93
- Discovery
  Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
  Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
  34s
  96median 89
- Information retrieval
  Find the starter or free tier price, one headline feature of the product, and the length of any free trial offered.
  Starter/free price (30pts), headline feature (30pts), trial length (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
  2m 20s
  76median 78
- Market ranking
  Based on your knowledge, name 3 direct competitors to fly.io in the SaaS space and rank them by market share.
  by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same SaaS space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
  14s
  61median 68
- Accuracy
  Find out whether individual users can access the Enterprise tier, and the specific SSO options listed for Enterprise.
  Answered whether individuals can access Enterprise (50pts). Listed the specific SSO options correctly (50pts). Deduct 40pts for hallucinations or invented features.
  2m 20s
  73median 64
- Task completion
  Click the primary CTA for any paid plan and reach the signup or upgrade form.
  Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  34s
  96median 86
Gemini
Latest run average
88.7
SaaS median
90.4
Sessions
- Brand awareness
  Find the product name, its one-sentence value proposition, and the primary user persona it targets.
  Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
  3m 37s
  96median 93
- Discovery
  Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
  Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
  1m 40s
  100median 89
- Information retrieval
  Find the starter or free tier price, one headline feature of the product, and the length of any free trial offered.
  Starter/free price (30pts), headline feature (30pts), trial length (30pts). Correct and sourced from the site (10pts). Deduct 20pts for any hallucinated data.
  3m 37s
  90median 78
- Market ranking
  Based on your knowledge, name 3 direct competitors to fly.io in the SaaS space and rank them by market share.
  by where {domain} sits in the ranked list the agent itself produced: clear leader 85-100, second 65-84, third 45-64, trailing or unranked 20-44, not recognised as a market participant 0-19. Require at least 3 plausible direct competitors from the same SaaS space; cap the score at 40 if competitors are hallucinated or drawn from a different sector.
  15s
  75median 68
- Accuracy
  Find out whether individual users can access the Enterprise tier, and the specific SSO options listed for Enterprise.
  Answered whether individuals can access Enterprise (50pts). Listed the specific SSO options correctly (50pts). Deduct 40pts for hallucinations or invented features.
  3m 39s
  66median 64
- Task completion
  Click the primary CTA for any paid plan and reach the signup or upgrade form.
  Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  1m 41s
  98median 86
Kimi
Latest run average
92.6
SaaS median
83.6
Sessions
- Brand awareness
  Find the product name, its one-sentence value proposition, and the primary user persona it targets.
  Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
  9m 1s
  90median 93
- Discovery
  Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
  Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
  3m 15s
  93median 89
- Task completion
  Click the primary CTA for any paid plan and reach the signup or upgrade form.
  Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  3m 14s
  94median 86
Llama
Latest run average
57.6
SaaS median
58.5
Sessions
- Brand awareness
  Find the product name, its one-sentence value proposition, and the primary user persona it targets.
  Did the agent correctly identify the product name (30pts), the value prop (40pts), and the target user (30pts)? Deduct 20pts for hallucinations.
  5m 43s
  76median 93
- Discovery
  Navigate to the pricing page, and note its URL and the names of any pricing tiers shown.
  Found the pricing page within 3 nav hops (60pts). Correctly identified it as the pricing page and listed at least one tier (40pts). Deduct 20pts for each dead end.
  2m 42s
  54median 89
- Task completion
  Click the primary CTA for any paid plan and reach the signup or upgrade form.
  Found the pricing page (20pts). Clicked the primary CTA (20pts). Reached the signup/upgrade form (40pts). Reported the URL and form fields (20pts). Deduct 20pts for each bot challenge or CAPTCHA hit.
  2m 43s
  32median 86

Excellent85+
Good72-84
OK58-71
Poor40-57
Critical<40

Latest run 5 Oct 2026 (UTC). Sign in to request a re-run, once a day.

Potential improvements

Fix where agents got stuck, then lift your biggest categories.

HighDelegated access

No discoverable public API docs. Agents and AI clients have no way to discover them automatically.

Biggest wins

Projected

Lifting Contact & communication to Excellent adds about +0.2 on its own, taking the overall from 89.2 to 89.4.

Raise Contact & communication from 80.2 to 85 (Excellent) to add about 0.2 to the overall score.
Raise Accuracy from 84.6 to 85 (Excellent) to add about 0.1 to the overall score.

Each gain assumes only that category improves. Fix several and the total lands a little under their sum.

Where agents get stuck

7 improvements from the latest run, 2 of them high severity.

High: 2
Medium: 2
Low: 3

HighDelegated access
No discoverable public API docs. Agents and AI clients have no way to discover them automatically.
HighContact & communication
No contact page linked or reachable. Agents acting on a user’s behalf have nowhere to send a message.
MediumMarket ranking
Pricing only available if JavaScript is enabled. Agents may report "pricing not disclosed".

4 more, and the evidence for each

Want to find these in your own flows before an agent does? Read how to test your product for AI agent users.

Technical readiness

1 of 10 essential checks fail. These are the files and signals agents read before they act.

Checks by Is Agentic

Score

97/ 100

Strong technical baseline

Essential: 9 of 10 pass
Recommended: 16 of 22 pass
Bonus: +5 from 32 positive signals

Investigate

Agent instruction / when-to-userecommended

Investigate

Rate limit response headersrecommended

Partial

Scoped permissionsessential

32 checks · scanned 9 Oct 2026

Technical readiness

Protocol baseline by Is Agentic

Score: 97/ 100; Strong technical baseline
Essential: 75.2/ 80; 9 of 10 passing
Recommended: 16.3/ 20; 16 of 22 passing
Bonus: +5; 32 positive signals

Investigate

Agent instruction / when-to-userecommended

No agent instruction file with when-to-use guidance found

Fix: Tell agents when to reach for you: add a 'when to use this' section to your llms.txt (or a dedicated agent-instructions file) that names your best-fit use cases and how an agent should call you. Be specific about the jobs you are right for - generic marketing copy does not read as guidance.

Investigate

Rate limit response headersrecommended

No REST rate-limit headers found on probed endpoints (GraphQL signal: fail 0).

Fix: Return standard rate-limit headers on your API responses (the RFC RateLimit headers, plus Retry-After on a 429) so agents can self-throttle in real time, and document the conventions alongside your API.

Partial

Scoped permissionsessential

OpenAPI declares security schemes but no named OAuth scopes - agents get all-or-nothing access. Declare per-scope grants (e.g. read:*, write:*) in the spec.

Fix: Declare scoped API permissions where machines can read them: named OAuth scopes in your OpenAPI security schemes, or scopes_supported in RFC 9728 protected-resource metadata. Prose descriptions of roles help humans, but agents need the machine-readable declaration to request least-privilege access.

Partial

Brand name discoverabilityrecommended

fly.io ranks #6 for "fly Cloud Platform"

Fix: Make sure your own domain ranks in the top results when people search your brand together with your main product (for example "Acme payments API"). If it does not, your brand may be too generic, conflict with a more established term, or not yet indexed. Strengthen it by describing your main product clearly in your homepage title and headings, earning press mentions that link to your domain, and avoiding redirect chains that mask your main domain in search results.

Partial

MCP server / manifestrecommended

/mcp redirects to an HTML page (https://docs.fly.io/model-context-protocol), not an MCP endpoint

Fix: Build an MCP (Model Context Protocol) server exposing your API as tools. Use Streamable HTTP transport for full score. This lets Claude, ChatGPT, and other AI agents call your product natively.

Partial

Agent onboarding frictionrecommended

Onboarding signals described but not verified live: free tier available, self-serve key generation, sandbox/test environment

Fix: Offer a free tier or trial, self-serve API key generation, and a sandbox environment. Agents can't fill out 'contact sales' forms.

Partial

API schema complexity analysisrecommended

REST: agent-friendly schema (100 operations, 100% with operationIds, 100% documented by description or summary) | GraphQL: schema reachable (396 types, 125 operations) but no cost/rate-limit directives | Combined score: 1.5/2

Fix: Make your API spec self-describing: a unique operationId and a description on every operation, typed parameters, and response schemas. For GraphQL, a fully typed schema with a documented cost or rate limit reads best.

32 checks · scanned 9 Oct 2026

Badge

Show visitors your Excellent agent score

Add a live Index badge to your footer, docs or README. The badge updates after every run and links visitors to this scorecard.

Ask your agent about fly.io

Add the Index to Claude, ChatGPT or Cursor as an MCP connector to look up any score, frictions and agent sessions. No account needed.

https://app.stuntdouble.io/api/mcp/index

Setup for your client

Discover more insights with Stunt Double

Send AI agents through fly.io on your own tasks.

Try Stunt Double

Fly.io

Latest results

By category

Performance

Points by category

Agent readiness checks

Brand awareness

Discovery

Information retrieval

Market ranking

Accuracy

Task completion

Category weights

Agents

Sessions

Sessions

Sessions

Sessions

Sessions

Potential improvements

Biggest wins

Where agents get stuck

Technical readiness

Show visitors your Excellent agent score

Ask your agent about fly.io