Dialog
Also known as: Dialog AI, askdialog
Ecommerce AI shopping agent that encodes a brand's identity and expertise to advise and sell on the site and inside AI assistants like ChatGPT and Gemini.
Dialog is an AI sales agent for ecommerce, founded in 2022 in Paris by Antoine Grimal and Louis Pinsard and used by more than 300 brands including Shiseido, Delsey, MG Motor and Manucurist. Its argument is that ecommerce sites are glorified spreadsheets, with categories, filters and search bars designed around the technical limits of the early 2000s instead of around how customers actually decide. Dialog replaces that navigation with a conversation.
The platform encodes a brand across three dimensions. Identity covers voice, codes and positioning, so the agent speaks the way the brand does. Responsibility covers the guardrails, policies and escalation rules the brand sets for its customers. Expertise covers product knowledge, sales logic and recommendations, built on how the brand's best sellers advise. Underneath, Dialog ingests the live catalog alongside internal documentation and content, and follows the catalog as it changes without manual updates.
Four named modules sit on that foundation. The AI Personal Shopper runs conversational discovery across the catalog, replacing static quizzes with questions or even a photo. The AI PDP Assistant answers technical questions and handles objections on the product page itself, at the moment a shopper hesitates. Smart Reengagement identifies hesitant shoppers from what they asked but did not buy and captures contact details in the conversation. Conversation Insights turns every question asked into a reporting layer on objections, unmet needs and gaps in the catalog or content.
The agent runs where customers shop. It is embedded natively across the brand's homepage, product pages and search, and inside external assistants including ChatGPT, Perplexity and Gemini, so the brand keeps control of how AI platforms sell its products. Teams review past conversations and continuously tune how the agent answers, recommends and escalates.
Developers integrate through a TypeScript SDK on npm, a CDN script or a Shopify app, and a developer mode adds external API calls, custom rules, webhook triggers and separate agents per country, catalog or persona. Dialog shows SOC 2 and GDPR badges on its homepage but publishes no report, trust portal or customer-facing access controls, and offers no data residency options, which a regulated customer should weigh.
Vendor details
Canonical URL
https://www.askdialog.com
Category
GTM / revenue agent
Funding status
Seed of EUR 3.7M (about $4.4M) led by Galion.exe with Kima Ventures, Weaving, startup studio Hexa, and angels from Criteo, Hugging Face, Decathlon, and AB Tasty (November 2025). Founded 2022 in Paris. Co-founders Antoine Grimal (CEO) and Louis Pinsard (CTO). Reports 300+ brands and 300,000+ add to cart events.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Embeds across a brand's homepage, product pages, and search, with a Shopify app, a TypeScript SDK and CDN script, cart and product hooks (addToCart, getProduct), and assistant events. Also surfaces the brand agent inside external AI assistants such as ChatGPT, Perplexity, and Gemini for agent to agent commerce.
In practice
A shopper lands on your store and cannot tell which product fits. Dialog's AI Personal Shopper asks about their needs, or works from a photo they share, recommends from your live catalog and adds the pick to the cart.
A shopper hesitates on a product page and leaves without buying. The AI PDP Assistant answers the technical question on the page, and if they still leave, Smart Reengagement captures their contact details and passes them to your email or CRM tool for a follow-up.
Your merchandising team wants to know why shoppers stall. Conversation Insights logs every question asked and surfaces recurring objections and gaps in the catalog, and the team reviews past conversations to tune how the agent answers, recommends and escalates.
Sources & related URLs
Related / legacy domains
Research sources
Agentic Index coverage score
9.0 / 14 capabilities · 64%
| Integrations & Tool Calling | Full |
|---|---|
|
The agent acts in systems Dialog does not own, and a customer can add connections of its own. Dialog installs as a Shopify app and embeds through an SDK and CDN script that expose cart management and product fetching, so the agent adds to cart in the merchant's store instead of only advising. Smart Reengagement captures a shopper's contact details in conversation and pushes them into the brand's connected email or CRM system. Developer mode adds external API calls, webhook triggers and custom rules, so the set of connections is not fixed. Reach extends onto external assistants including ChatGPT, Perplexity and Gemini, where the brand's own agent answers. Sourceapps.shopify.com/dialog-ai-sales-assistant, npm SDK and askdialog.com/agentic-commerceread 2026-09-01 |
|
| Workflow Orchestration | Partial |
|
Dialog runs guided conversational sales flows that qualify a shopper's needs, recommend products with encoded recommendation logic and sequencing, and drive toward purchase. There is no complex multi step or multi agent orchestration. Sourceaskdialog.com/agentic-commerceread 2026-10-01 |
|
| Knowledge Grounding & RAG | Full |
|
The agent works from a structure built over the brand's own material, which Dialog calls encoding, not prompting. Dialog ingests the live catalog alongside the brand's documentation and content. The third encoding dimension, expertise, covers product knowledge, sales logic and recommendations, built on how the brand's best sellers advise. That store persists, follows the catalog as it changes, and is read at conversation time to answer product questions and drive recommendations, with dynamic FAQs assembled from real shopper questions on top of it. Dialog says the agent is trained on the brand's catalog and tone, but what it describes is ingestion and retrieval, not fine tuning. Sourceaskdialog.com/agentic-commerceread 2026-09-01 |
|
| Human Oversight & Guardrails | Full |
|
Dialog encodes a brand across three dimensions, identity, responsibility and expertise. Responsibility covers guardrails, policies and escalation, the rules the brand sets for its customers. The agent hands off under conditions the brand defines, and the same interface lets a team tune how it answers, recommends and escalates. Dialog names the guardrails as a pillar but gives no detail on them. There is no per action gate, permission model or escalation configuration. Sourceaskdialog.com/agentic-commerce, brand encoding sectionread 2026-09-01 |
|
| Security, Identity & Governance | Partial |
|
An AICPA SOC 2 badge and a GDPR badge appear on Dialog's site. Shopify's data governance belongs to Shopify, not Dialog. There is no named control for customers, such as single sign on, role based access control, audit logging or retention configuration, and no public SOC 2 report or trust portal. Sourceaskdialog.com homepage badge rowread 2026-09-15 |
|
| Observability & Auditability | Partial |
|
Teams can review past conversations, and Conversation Insights logs and analyzes every question a shopper asks to surface recurring objections and gaps, with the SDK emitting positive and negative feedback events per response. Dialog calls this no black box. For a conversational agent the transcript is a genuine record of what it did. There is no audit log, run history, decision trace or record of which catalog item or rule produced a given answer, so the transcript is the only record. The analytics layer describes shopper behavior, not agent execution. Sourceaskdialog.com/solutions/conversation-insights and the npm SDK feedback eventsread 2026-09-01 |
|
| Memory & State Persistence | Partial |
|
Per-shopper state outlives the conversation. Smart Reengagement identifies hesitant shoppers on what they asked but did not buy and carries that into a follow-up, so the exchange is retained and read back instead of discarded at session end. No memory feature is named, scoped or given a lifetime. The persistent brand encoding of identity, guardrails and expertise is configuration, not memory. Sourceaskdialog.com/solutions/smart-reengagement and askdialog.com/agentic-commerceread 2026-09-01 |
|
| Deployment & Data Residency | Not documented |
|
Dialog is delivered only as a hosted service, embedded through a script, an npm package or a Shopify app, with nothing the customer selects. There is no region choice, data center disclosure, VPC, private tenancy or self hosted option. The developer mode option for an agent by country is audience segmentation, not data residency. Sourceaskdialog.com/agentic-commerce and npmjs.com/package/@askdialog/dialog-sdkread 2026-09-01 |
|
| Prebuilt Agents / Templates / Packs | Full |
|
Four prebuilt agent modules ship by name, each with its own product page. AI Personal Shopper handles conversational discovery across the catalog, AI PDP Assistant answers questions and handles objections on the product page, Smart Reengagement identifies hesitant shoppers and captures contact details, and Conversation Insights turns conversations into merchandising and content signals. A brand switches these on instead of assembling them. Sourceaskdialog.com solutions pages and site navigationread 2026-09-01 |
|
| Triggers & Channel Coverage | Full |
|
The merchant's own customers start the agent's work, not the merchant's staff. A shopper's question on the homepage, a product page or search, or inside ChatGPT, Gemini, Claude or Perplexity, wakes the agent with no one at the merchant starting it, and a Smart reengagement module reaches back out to shoppers. Sourceaskdialog.comread 2026-10-01 |
|
| Model Flexibility & Routing | Not documented |
|
The model provider is not named, and the customer cannot select a model or route across providers. ChatGPT, Gemini and other assistants are places the agent is distributed, not model choices. Sourceaskdialog.com/agentic-commerceread 2026-09-01 |
|
| APIs / SDKs / MCP Extensibility | Full |
|
The TypeScript SDK ships on npm as @askdialog/dialog-sdk, instantiated with an API key, with a CDN build exposing DialogSDK on the window for teams not using a package manager, and covering assistant interactions, product fetching, cart management, appearance customization and feedback events such as userSendPositiveFeedback and userSendNegativeFeedback. Alongside it, a developer mode triggers external API calls, injects custom rules, fires webhook triggers and manages multiple agents per country, catalog or persona. Sourcenpmjs.com/package/@askdialog/dialog-sdk and askdialog.com/agentic-commerceread 2026-09-01 |
|
| Testing, Debugging & Optimization | Full |
|
The customer runs an optimization loop on the agent, which Dialog calls Continuously test, evaluate and improve. It has four steps, all in one interface. Teams review past conversations, understand how users behave, fine-tune how the agent answers, recommends and escalates, and improve performance. Dialog frames it as no black box. The loop tunes and measures the agent's own behavior, not a downstream business metric. There is no A/B testing of agent versions. Sourceaskdialog.com/agentic-commerceread 2026-09-01 |
|
| Browser / Computer-use | Not documented |
|
Dialog is an embedded conversational agent (including photo based multimodal input) but performs no browser automation or general computer use. Sourceaskdialog.com/agentic-commerceread 2026-10-01 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Pricing
No public list pricing. Access starts with a demo, and Dialog is also available as a Shopify app on channel terms.
Not published. No billing unit is stated on the site.
Cost watchouts
The Shopify app carries its own plan tiers on channel terms, separate from direct pricing. Larger brand deployments go through a demo, and no direct price, usage meter or scaling rule is published.
Variable cost rationale
Dialog publishes no billing unit, so what is metered is not stated. No plan fee, usage meter, cap or commitment appears on the site, and the Shopify app's plan prices are channel terms rather than the direct price. Nothing public shows what makes the bill grow or what limits it.
Sales call required
Mixed (some tiers require a call)
Free / trial
No trial terms published. Access is through a demo or the Shopify app install.
Lowest paid plan
Not published
Key ambiguities
No public rate card is published. A self serve Shopify install exists alongside a book a demo motion for larger brands, so the pricing structure is unclear.
Related vendors
- 11x — AI digital workers (Alice for outbound SDR work, Julian for inbound…
- 1up — AI answer engine for sales teams that automates RFPs and security…
- Actively AI — GTM superintelligence platform that trains a custom reasoning model…
- Aircover.ai — AI sales assistant that delivers real time in call coaching, a…
- AiSDR — AI SDR platform with multichannel outreach automation, quota visible…
- Akkari — Autonomous customer ops agent that captures every commitment,…
Alternatives to Dialog
The closest documented capability profiles to Dialog among GTM and revenue agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Podium9.0 / 14Fuller documented coverage on Workflow Orchestration
- Amplemarket9.5 / 14Fuller documented coverage on Workflow Orchestration and Security, Identity & Governance
- Mutiny8.5 / 14Fuller documented coverage on Workflow Orchestration
- 11x8.0 / 14Fuller documented coverage on Workflow Orchestration
- Actively AI8.0 / 14Fuller documented coverage on Workflow Orchestration
- Botify10.0 / 14Adds documented Browser & Computer Use
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded