AI Agent App
AI Agent App is a multi-agent automation platform. Per the vendor's own homepage, agents plan a sequence of steps, execute them and report back, looping until the task is done or a human review gate is reached, and hand off to each other in multi-agent teams. Read access is the default and changes still require the user's approval. The page names PostHog, Stripe, Gmail, GitHub, Linear and Notion as systems it connects to and acts across; no broader integration count is published on the capture checked. The vendor reports over 61,392 users. No compliance certification, audit trail, third-party evaluation, insurance, indemnity or outcome-linked payment term is published on the page checked.
19 fields evidenced · 40 with no public information. Every value below links to the document it came from and the date we checked it.
10 of those are quoted but not yet interpreted: we hold the source sentence and the date we read it, but nobody has written the answer to the question yet. Those rows show the quote and say so rather than repeating it back as an answer. Why these exist
2 of those are flagged for review: our own check found language in the cited source that may address the field. An editor has not adjudicated them yet.
4 of the evidenced values quote wording our own later capture of the same page no longer contains. Marked below, awaiting an editor.
Trust gap
How this is scoredAre scope, spend, and authority enforced while the agent runs?
Proposed writes wait for explicit human approval before executing, which bounds authority at run time; no evidence of enforced scope, spend or authority limits.
Judged Aug 3, 2026; evidence newer. We have since re-read Runtime governance and Permission scopes, most recently on Aug 13, 2026. No one has re-scored this dimension against them — the score above stands, but it is older than the evidence below it. How current a score is
How this gap gets closed →Is there a tamper-evident record of what it actually did?
No public evidence found on the page checked.
Judged Aug 3, 2026; evidence newer. We have since re-read Audit trail and Tamper-evident log, most recently on Aug 13, 2026. No one has re-scored this dimension against them — the score above stands, but it is older than the evidence below it. How current a score is
How this gap gets closed →Are compliance obligations attached per engagement?
No public evidence found on the page checked.
Judged Aug 3, 2026; evidence newer. We have since re-read Compliance certifications and Regulatory alignment, most recently on Aug 4, 2026. No one has re-scored this dimension against them — the score above stands, but it is older than the evidence below it. How current a score is
How this gap gets closed →Does payment depend on a verified result?
No public evidence found on the page checked.
Judged Aug 3, 2026; evidence newer. We have since re-read Outcome-based pricing and Settlement mechanism, most recently on Aug 4, 2026. No one has re-scored this dimension against them — the score above stands, but it is older than the evidence below it. How current a score is
How this gap gets closed →Can the deployment be insured, and is the customer indemnified?
No public evidence found on the page checked.
Judged Aug 3, 2026; evidence newer. We have since re-read Insurance available, Insurance carriers, Coverage limits and Indemnification, most recently on Aug 4, 2026. No one has re-scored this dimension against them — the score above stands, but it is older than the evidence below it. How current a score is
How this gap gets closed →Assurance
- Insurance available
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Own liability cover
- no public informationaiagent.app · checked Aug 13, 2026 · source did not state this
- Insurance carriers
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Coverage limits
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Indemnification
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Liability cap
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Audit trail
- Agent execution steps are logged as a "work log" with live progress, visible to the user
“The steps an agent took are now labelled as a work log, with live progress while it runs and clearer follow-up prompts on your home screen.”
aiagent.app · checked Aug 13, 2026 - Tamper-evident log
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Explainability
“AI Operations Agent Thought for 4s · scanned 7 days of funnel events”
aiagent.app · checked Aug 4, 2026- Runtime governance
- Plan limits enforced at workflow activation time only; in-flight runs cannot be halted by a plan check
“Limits are checked when you activate a workflow, never while one is running. Nothing already in flight can be stopped by a plan check.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 10, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
aiagent.app · checked Aug 13, 2026 - Permission scopes
- Read access by default; write/changes require explicit user approval
“Company Brain can read your data, but changing it still needs your approval.”
aiagent.app · checked Aug 11, 2026 - Compliance certifications
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Regulatory alignment
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Outcome-based pricing
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Settlement mechanism
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Asset custody
- no public informationaiagent.app · checked Aug 13, 2026 · source did not state this
- Dispute process
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- SLA terms
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Evaluation coverage
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Self-reported performance
- no public informationaiagent.app · checked Aug 13, 2026 · source did not state this
Agency
- Autonomy level
“An AI agent acts on behalf of a user or organisation with minimal human input — connecting to external tools, reading live data, and taking approved actions to complete a job end to end.”
aiagent.app · checked Aug 4, 2026- Human oversight
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Goal complexity
“They combine large language models , persistent memory , tool use , and goal-directed behaviours — looping until the task is done or a human review gate is reached.”
aiagent.app · checked Aug 4, 2026- Action space
“connecting to external tools, reading live data, and taking approved actions”
aiagent.app · checked Aug 4, 2026- Operating environment
- Connects to and acts across PostHog, Stripe, Gmail, GitHub, Linear, Notion
“posthog stripe gmail github linear notion”
aiagent.app · checked Aug 11, 2026 - Initiative
“Unlike a chatbot that waits for each prompt, an AI agent plans a sequence of steps, executes them, and reports back.”
aiagent.app · checked Aug 4, 2026
Safety
- Safety evaluations
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Red teaming
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Safety policy
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Usage restrictions
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Model or system card
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Incident reporting
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Third-party evaluations
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Data handling
“Every task your AI Agents complete is encrypted and protected by default. From automation to data handoff, your workflows are secured with enterprise-grade standards—so you can scale safely, without compromise. End-to-end security for every task Your AI Agents operate in a secure, encrypted environment. From task execution to data handling, every step is protected by default—so you can trust your AI workflows without compromise.”
aiagent.app · checked Aug 4, 2026
Practicality
- Pricing model
“How much does AI Agent cost? Is there a free plan?”
aiagent.app · checked Aug 4, 2026- Price point
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Availability
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Deployment options
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Integrations
- Event and inbound-webhook triggers for firing workflows (paid-plan capability)
“Event and webhook triggers. Firing a workflow from an event or an inbound webhook is a paid-plan capability, listed on the plan rather than discovered by trial.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 10, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
aiagent.app · checked Aug 13, 2026 - Supported regions
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Support model
- Offers direct sales call booking and a contact form
“book a call, or send a message through a proper contact form”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 10, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
aiagent.app · checked Aug 13, 2026
Foundation models
- Base models
- large language models
“They combine large language models , persistent memory , tool use , and goal-directed behaviours”
aiagent.app · checked Aug 4, 2026 - Model provider
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Model swappable
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Open weights
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Fine-tuning
- no public information
Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences
aiagent.app · checked Aug 4, 2026 - Context window
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
Ecosystem
- Protocols supported
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Tool use
- tool use
“They combine large language models , persistent memory , tool use , and goal-directed behaviours”
aiagent.app · checked Aug 4, 2026 - Multi-agent
“Multi-agent teams Agents that hand off to each other — research, analyze, then draft.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 10, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
aiagent.app · checked Aug 4, 2026- API access
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Open source
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Marketplace presence
- no public information
Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences
aiagent.app · checked Aug 4, 2026
Impact
- User base
“Over 61,392 users run their workflows on AI Agent.”
aiagent.app · checked Aug 4, 2026- Deployment scale
“Over 61,392 users run their workflows on AI Agent.”
aiagent.app · checked Aug 4, 2026- Target sectors
- Growth Growth Marketing Sales Support Product Growth & Analytics
“Operators across every department put AI agents to work — the more teams adopt it, the sharper the whole organisation gets. Growth Growth Marketing Sales Support Product Growth & Analytics”
aiagent.app · checked Aug 4, 2026 - High-risk domains
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Documented incidents
- no public informationaiagent.app · checked Aug 4, 2026 · source did not state this
- Market recognition
- no public informationaiagent.app · checked Aug 13, 2026 · source did not state this