dassi
dassi is a browser-based AI agent that automates recurring web tasks by learning your workflow once in plain English, then executing on a schedule you define. It runs in Chrome, Edge, or Brave, operates within accounts you're already signed into, and pauses for your approval on flagged actions before proceeding. The agent integrates with Claude, ChatGPT, Gemini, and other LLMs, caches context within runs to reduce token costs, and writes site-specific JavaScript libraries so repeat executions cost less. Best suited for e-commerce payout reconciliation, recruiting applicant screening, and back-office report building, dassi lets agencies offer low-touch automation retainers without building custom integrations or managing API keys on behalf of clients.
dassi is an AI agent, priced at $10/month on the dassi for developers plan, integrating with Claude, ChatGPT, Gemini, and Grok. InnovaAI scores it 5.3/10 for agency resale.
Agency Audit
dassi automates recurring web tasks by running as a browser agent in Chrome, Edge, or Brave, executing workflows you teach it once in plain English. It integrates with Claude, ChatGPT, Gemini, and other LLMs, and works within accounts you're already signed into, no separate integrations required. Agencies can resell dassi to e-commerce clients (payout reconciliation), recruiting teams (applicant screening), and back-office operations, positioning it as a low-touch automation retainer. The model works best for clients with 3-5 repeatable tasks per month; agencies should expect 15-30 minute setup per client and recurring support for workflow refinement.
5.3/10
40%
2d 1-2 days
- Your clients run e-commerce or recruiting operations and need weekly payout reconciliation or applicant screening without building custom integrations.
- You want to offer a low-touch automation retainer that doesn't require API wiring or third-party integration management on your side.
- Your clients are already signed into their own web apps (Shopify, LinkedIn Recruiter, ATS platforms) and you can teach dassi their specific workflows once.
- Your clients need 24/7 unattended automation or server-side scheduling independent of browser sessions.
- You require white-label branding or a client-facing portal; dassi displays its own brand in the browser extension and does not offer verified white-label surfaces.
- Your clients operate in regulated industries requiring SOC2 Type II or HIPAA compliance; dassi's compliance posture is not documented beyond general browser-based execution.
Profit Path
$10/mo
$600–$1.5K/project
Monthly Recurring
From 242 published agency rates in USA, 25th to 75th percentile x 20h of assumed delivery time. Rates are self-reported directory profiles, not observed transactions.
Platform Features
Core capabilities of dassi
Plain-English workflow teaching
Describe a task in plain English or walk dassi through it once while it watches your browser. No API keys, context pasting, or integration wiring required. dassi reads the pages you're logged into and learns your specific workflow.
Scheduled execution with approval gates
Set a schedule (daily, weekly, on-demand) and flag which actions require your approval before execution. dassi pauses and notifies you via email or Telegram when it hits a decision point, then resumes once you approve.
Multi-LLM support
Connect Claude, ChatGPT, Gemini, Grok, DeepSeek, Kimi, or OpenRouter to power the agent. Bring your own API keys or use existing ChatGPT accounts without separate authentication.
Context caching and site-specific libraries
dassi caches context within a run and writes JavaScript libraries per site, so repeat executions cost less in LLM tokens. Each subsequent run calls learned functions instead of re-reading the page.
Payout and order reconciliation
Reconcile marketplace payouts against orders, flag mismatches, and write results to Google Sheets or Excel. Pause before opening support cases or messaging marketplaces.
Applicant screening and ATS integration
Screen new job applicants against your criteria, score them, and write notes back into your ATS. Runs on a daily schedule and flags candidates requiring manual review.
What Makes dassi Different
Unique advantages vs similar tools in this niche
Runs in your existing signed-in browser session with no integrations or stored credentials
vs Cloud browser agents that require API access or credential handoffIt works on the accounts you're already signed into, no passwords to hand over, no credentials stored, no logins copied anywhere.
Cuts repeat-run cost via context caching and self-written per-site JavaScript libraries
vs Browser agents that re-read pages and re-derive selectors every runWithin a run, dassi keeps the job's context byte-stable, so every step after the first reads it from your model provider's cache, up to 90% off input tokens on Claude.
Keeps a persistent, editable correction memory across runs
vs Chat assistants where corrections die when the conversation endsThe correction goes into a memory you and dassi can both read and edit, so it carries into the next run instead of dying in the chat.
Latest Updates
Recent releases and improvements for dassi
Invite Friends for Credit & Broader PDF Support
New2026-09-18Added an Invite Friends program with credit rewards, expanded PDF support including scanned documents, and fixed a credit-check glitch that could reject valid API keys.
Smarter API Key Setup & a Cleaner Model Picker
Improvement2026-09-17Saving your own API key now automatically selects that provider, and the model picker has been cleaned up to show only curated, supported models.
Shared Voice Transcription, Simpler Folder Permissions & More Reliable Gmail Replies
Improvement2026-09-16Voice transcription shared between side panel and Telegram, simpler folder access permissions, more reliable Gmail replies, and added MCP access for browser tasks.
Native Clipboard Paste, More Reliable Dropdowns & Power-User REPL Upgrades
Improvement2026-09-15Dassi can now paste directly from clipboard using native browser paste, improved dropdown selection consistency, and REPL now supports network activity inspection and bulk text insertion.
Persistent Project Files, Live Scheduled Task Names & More Accurate Rich-Text Typing
Improvement2026-09-14Project files persist across conversations, scheduled workflows show task name during active runs, and improved rich-text typing accuracy preserving tabs and line breaks.
Investment ROI Calculator
Value equation analysis for dassi, based on the Hormozi framework
What is the Hormozi framework? A four-factor score: (what the service delivers × how reliably it delivers) divided by (how long it takes × how much effort it requires). A higher Value Multiplier means a better return on the time and money invested: faster, easier, and more proven results.
2.5× value multiple: invest $10/mo and agencies typically charge $600–$1.5K/project for the work it powers.
Why This Succeeds
Higher is betterClient Results Potential
What your clients actually get
Incremental gains: position as part of a larger solution stack
Save ~64 hours of your work each month
Reliability Score
How consistently this delivers results
Reliable with proper setup: most agencies see consistent delivery
Trusted by 30,000+ Chrome usersRated 4.8/5 on Chrome Web Store
Implementation Challenges
Lower is betterTime to First Revenue
How long until you can start earning
Standard ramp-up: accelerate to 1 day with Academy SOPs
Expect a few days from signup to first client delivery
Setup Effort
What it takes to get running
Near-turnkey: minimal setup before you can sell
Moderate effort: standard configuration with some customization needed
Strong ROI. dassi at $10/mo supports market rates of $600–$1.5K. Its 2.5× value-equation score weighs client outcome and likelihood against the time and effort to deliver, not cost.
Pricing
dassi platform cost to your agency
Starts at $10/mo (dassi for developers), scales to $300/mo (Max)
Starter
- Connect your own API keys
- dassi CLI
- Email and community support
- Save ~16 hours of your work each month
Pro
- Priority email support
- Save ~64 hours of your work each month
Max
- Priority support, fastest response
- Save ~200 hours of your work each month
dassi for developers
- Bring your own API keys
- Connect ChatGPT, Gemini, Claude and more
- dassi CLI
No verified white-label program for dassi: client-facing delivery runs under the platform's native branding.
Market Intelligence
How agencies monetize dassi: real offer economics and market positioning
- Small business owners with recurring back-office tasks
- Recruiting teams screening applicants
- E-commerce operators reconciling payouts
- Teams needing fully headless cloud automation without an open browser
- Users who cannot supply or manage an AI model key
Project-Based
ai-toolsAgency charges per-project fee for implementation. Ongoing optimization as optional retainer.
Offer Economics: What You Charge vs. What It Costs
Margin includes platform cost + agency labor at $75/hr.
Local service businesses (salons, clinics, contractors) with repetitive web tasks like appointment checks, review monitoring, or form submissions
Funded startups and regional brands needing multi-step browser automations across CRMs, ad platforms, or reporting dashboards
Multi-location or multi-department companies (50–500 employees) with high-volume repetitive web operations across marketing, ops, or finance tools
Enterprise organizations (500+ employees) seeking systematic browser-based automation across multiple business units, tools, and compliance-sensitive workflows
Scale Economics: Based on Starter Offer
Using dassi Task Starter Pack at $1.8K/client. Platform: $10/mo. Labor: 4h/client × $75/hr.
Net = MRR - platform cost - labor (4h/client × $75/hr).
Investment Decision Framework
Strategic vetting analysis for dassi
Consider
Favorable fit, worth a closer look
Buy If
4You want to offer a low-touch automation retainer that doesn't require API wiring or third-party integration management on your side.
Your clients run e-commerce or recruiting operations and need weekly payout reconciliation or applicant screening without building custom integrations.
Your clients are already signed into their own web apps (Shopify, LinkedIn Recruiter, ATS platforms) and you can teach dassi their specific workflows once.
You need a tool that caches context and reduces LLM token spend on repeat runs, making the unit economics work for smaller clients.
Skip If
4Your clients need 24/7 unattended automation or server-side scheduling independent of browser sessions.
You require white-label branding or a client-facing portal; dassi displays its own brand in the browser extension and does not offer verified white-label surfaces.
Your clients operate in regulated industries requiring SOC2 Type II or HIPAA compliance; dassi's compliance posture is not documented beyond general browser-based execution.
You need multi-tenant client reporting or a dashboard to monitor all client workflows from a single agency pane; dassi is single-user per browser instance.
Bottom Line
dassi automates recurring web tasks by running as a browser agent in Chrome, Edge, or Brave, executing workflows you teach it once in plain English. It integrates with Claude, ChatGPT, Gemini, and other LLMs, and works within accounts you're already signed into, no separate integrations required. Agencies can resell dassi to e-commerce clients (payout reconciliation), recruiting teams (applicant screening), and back-office operations, positioning it as a low-touch automation retainer. The model works best for clients with 3-5 repeatable tasks per month; agencies should expect 15-30 minute setup per client and recurring support for workflow refinement.
Reality Check
dassi runs only while your browser is open, so it cannot execute tasks on a true server schedule independent of user presence. Agencies reselling this must set client expectations around browser-active execution windows and handle escalations when flagged actions require approval but the client is offline.
Moderate effort: standard configuration with some customization needed
Academy for dassi
Work through it in order: the course for this service first, then the modules behind it.
No Academy modules are published for this service yet. Browse the full Academy
Why this category matters
The commercial case before the tooling.
Core concepts
The mental model you need to price and scope the work.
- Wiring Over WidgetsConcept
The AI agent itself is a commodity, but the value for agencies lies in the integration layer: connecting a pre-built agent to a client's CRM, calendar, and review cycle. This framework shifts focus from selecting the 'best' agent to mastering the wiring process. For example, an agency using Vendasta's white-label AI receptionist for a local business must configure it to match the client's booking rules and follow-up cadence, turning a generic tool into a tailored service. As agentic AI adoption grows (77% of decision-makers now run agents in production), clients expect this customization. Agencies that treat agents as components and invest in repeatable wiring processes can charge retainers for ongoing optimization, rather than one-off setup fees.
- Wiring Over WidgetsConcept
The AI agent market sells finished workers, but the strategic value for agencies lies not in the agent itself, which is increasingly a commodity, but in the wiring that connects it to a specific client's CRM, calendar, and review cycle. This framework, 'Wiring Over Widgets,' argues that agencies that treat agents as components rather than products win. The agent is the widget; the wiring is the integration, customization, and ongoing optimization that turns a generic tool into a tailored solution. For example, a white-label platform like Vendasta provides AI employees, but the agency's role is to configure them for each local business's unique lead flow and follow-up process. This wiring is where retainer pricing originates, as it requires ongoing maintenance and adjustment. Recent research shows that 88% of B2B marketers face foundational gaps, meaning clients need help not just deploying agents, but ensuring their operations can support them. Agencies that master the wiring can charge a premium for the irreducible value they add.
- Integration MoatConcept
The Integration Moat framework holds that the durability of an AI agent engagement is determined by how deeply the agent is wired into a client's existing systems, not by the agent's underlying capability. Since the agent itself is increasingly a commodity, the switching cost for the client lives in the integrations: the CRM fields mapped, the calendar sync, the review-cycle triggers, and the exception-handling rules. Agencies that invest in this wiring create a moat that competitors offering generic agents cannot cross. For example, a white-label platform like Vendasta lets an agency deploy an AI receptionist for a local business, but the real value is in configuring it to the client's booking flow and follow-up cadence. With 77% of AI decision-makers now running agentic AI in production, clients expect this depth, and agencies that deliver it convert one-off projects into retainers.
Decision and risk
How to judge the fit, and the ways it goes wrong.
- AI Agents Rule: Wire the Agent, Not the ProductEvaluation Rule
Treat the AI agent as a commodity component and focus your value on the integration into the client's specific workflows, systems, and review processes.
- AI Agents Rule: Wire the Agent, Not the ProductEvaluation Rule
Treat the AI agent as a commodity component and charge for the integration into the client's specific systems and workflows.
- The Productized Agent Trap: Why AI Agent Services Stall Without Client-Specific WiringFailure Pattern
- The Agent-as-Product Trap: Why AI Agent Services Stall Without Client-Specific WiringFailure Pattern
8 modules selected for dassi
Frequently Asked Questions
Answers about pricing, setup, implementation
dassi is a browser-based AI agent that automates recurring web tasks by learning your workflow once in plain English. It runs in Chrome, Edge, or Brave, uses accounts you're already signed into, and executes on a schedule you set. Common use cases include reconciling payouts against orders, screening job applicants and updating your ATS, and building weekly reports from dashboards into your own template.
dassi offers 4 pricing tiers, starting at $25/mo (Starter) up to $300/mo (Max). Agencies typically achieve 40% profit margins when reselling to clients.
No verified white-label program. Client-facing surfaces display the dassi brand in the browser extension. You cannot present a fully branded portal or remove dassi branding from the agent interface itself, though you can teach clients their own workflows and manage their approval rules.
Yes. dassi natively supports Claude, ChatGPT, Gemini, Grok, DeepSeek, Kimi, and OpenRouter. You can bring your own API keys for any of these models, or sign in with an existing ChatGPT account without needing a separate API key.
Initial setup is 15-30 minutes per client once you've taught dassi the workflow once. The agent watches you perform the task in your browser, learns the steps, and then runs it on schedule. Refinement and approval-rule tuning typically takes another 10-15 minutes after the first run.
dassi works best for e-commerce operators reconciling payouts and orders, recruiting teams screening applicants and updating ATSs, small business owners with recurring back-office tasks, and agencies managing client account operations. Any client with 3-5 repeatable web-based workflows per week is a candidate.
No. dassi runs only while the browser is open. Scheduled tasks execute when the browser is active; if the client closes their browser, the task pauses until they return. Agencies should set client expectations around browser-active windows and handle escalations when flagged actions require approval but the client is offline.
Yes. dassi can write results to Google Sheets or Excel, and send approval requests and task results via email or Telegram. This allows agencies to build weekly reports or reconciliation summaries that land directly in client inboxes or shared sheets.