Os detalhes do produto são exibidos em inglês. Traduções em breve.
Fatos rápidos
- Preço
- $249.00 USD
- Versões ERPNext
- —
- Tempo de configuração
- 30 min
- Licença
- Uma vez perpétua
- Idiomas
- 11 idiomas
Compra Única
ERPNext AI Copilot
A build-to-order in-app AI assistant for ERPNext that answers business questions, executes document actions, generates charts and schedules reports in plain English across any DocType. ECOSIRE scopes, builds, installs and supports it — request a quotation to start.
$249.00USD
Sem pagamento agora. Isto envia um pedido de orçamento à nossa equipe — responderemos por e-mail com preços e próximos passos.
Recursos Principais
Natural-language query over live ERPNext data (Selling, Stock, Accounts, HR) resolved through the Frappe ORM, not raw SQL against the database
Curated catalog of parameterized query intents — the LLM classifies the question and fills validated parameters, so it never generates arbitrary SQL
Permission-aware execution: every read and write runs through `frappe.has_permission` and the user's role profile, honoring User Permissions and DocType-level restrictions
Action execution from chat — create, update, add comments to, or submit documents (e.g. Material Request, Lead, Expense Claim) via whitelisted server methods with a confirmation step
Auto-generated charts from a prompt, saved as native Dashboard Chart / Number Card and pinnable to any Workspace
Scheduled NL reports built on Frappe `scheduler_events` (cron/daily/weekly hooks) with delivery to email and WhatsApp
Multi-provider LLM support — OpenAI, Anthropic Claude, DeepSeek, or a self-hosted local model — switchable per environment via an `LLM Provider Setting` DocType
Full audit trail: prompts, resolved queries, actions and responses logged to dedicated DocTypes and written back via `hooks.py` doc events
In-app chat panel embedded in the ERPNext desk plus optional whitelisted REST endpoints for external/mobile clients
Context-aware answers that respect the active company, fiscal year and default filters, with results returned as table, narrative summary or chart
Client Script + custom page front end so the assistant is reachable from any DocType list or form view
Rate limiting and per-role token/cost budgets to keep LLM spend and abuse under control
Redaction and field-masking hooks so sensitive fields (salaries, margins) can be withheld from prompts sent to external providers
Compatible with Frappe/ERPNext v15 and v16, packaged as a standard installable app for `bench get-app` / `bench install-app`
Sobre este Produto
Your ops team already lives in ERPNext, but the answers they need are trapped behind Report Builder filters, Query Reports and a backlog of custom report scripts that only a developer can write. A manager who wants "top 10 customers by outstanding this quarter, grouped by territory" ends up pinging the ERPNext admin, who writes another one-off script or a Number Card. ERPNext's native dashboards and Insights cover pre-built views, but the moment a question is ad-hoc — or needs to also do something, like drafting a follow-up Sales Order — the native tooling runs out of road. Self-service stops where SQL and Server Scripts begin.
Por Que Escolher ERPNext AI Copilot
Natural-language query over live ERPNext data (Selling, Stock, Accounts, HR) resolved through the Frappe ORM, not raw SQL against the database
Curated catalog of parameterized query intents — the LLM classifies the question and fills validated parameters, so it never generates arbitrary SQL
Permission-aware execution: every read and write runs through `frappe.has_permission` and the user's role profile, honoring User Permissions and DocType-level restrictions
Action execution from chat — create, update, add comments to, or submit documents (e.g. Material Request, Lead, Expense Claim) via whitelisted server methods with a confirmation step
Auto-generated charts from a prompt, saved as native Dashboard Chart / Number Card and pinnable to any Workspace
Scheduled NL reports built on Frappe `scheduler_events` (cron/daily/weekly hooks) with delivery to email and WhatsApp
ERPNext AI Copilot is a proper Frappe app (erpnext_ai_copilot) that installs onto your existing bench and adds an in-app chat panel plus its own DocTypes (AI Copilot Session, AI Copilot Message, AI Copilot Report Schedule, LLM Provider Setting). It translates plain-English questions into safe, permission-aware queries against your live ERPNext data — Sales, Stock, Accounts, HR — using a curated catalog of parameterized queries and the Frappe ORM, never free-form SQL against your database. Every request runs through frappe.has_permission and the current user's role profile, so the Copilot can only read and write exactly what that user could do in the desk UI. Answers come back as a table, a narrative summary, or an auto-generated chart, and the user can pin any result to a Workspace or Dashboard Chart.
Beyond read-only analytics, the Copilot executes actions. Through whitelisted server methods it can create and update documents from chat — draft a Material Request, add a comment to a Lead, submit an approved Expense Claim — with a confirmation step and full audit trail written back via hooks.py doc events. Scheduled natural-language reports are built on Frappe scheduler_events: a user describes a report once ("every Monday 8am, this week's low-stock items below reorder level") and the Copilot delivers it to email or WhatsApp on a cron cadence. LLM access is provider-agnostic — OpenAI, Anthropic Claude, DeepSeek, or a self-hosted local model — configured per-environment so your data-handling and cost policy stay under your control, with prompts and responses logged for governance.
Because this is build-to-order, we start from your ERPNext, not a generic demo. After a short scoping call we confirm which DocTypes and modules the Copilot should cover, which roles get read versus write actions, your LLM provider and data-residency requirements, and the report/notification cadences your team needs. ECOSIRE then builds the app against your Frappe/ERPNext v15 or v16 version, tests it on a staging bench, runs UAT with your team, and installs it to production with a rollback plan. Typical delivery is 2–4 weeks from confirmed scope. You receive the full source, a git repository handover, documentation and training — there is no instant download, because we build it to fit your instance.
O que você ganha
- Installable source code for your version of the app (`erpnext_ai_copilot`), packaged for `bench get-app` / `bench install-app`
- Installation and configuration on your bench, including LLM provider wiring and role/permission setup
- Technical documentation: DocType reference, whitelisted methods, hooks.py events, scheduler config and query-intent catalog
- User guide plus a live training session for admins and end users
- UAT on a staging bench with a documented rollback plan before production install
- Post-go-live support window for bug fixes and configuration adjustments
- Private git repository handover with full commit history and versioned releases
- Query-intent and prompt catalog tuned to your DocTypes so future intents can be added by your team
Para quem é isso
ERPNext Administrator
Owns the bench and the site config. Tired of writing one-off Query Reports and Server Scripts for every ad-hoc data request. Wants self-service analytics that still respects permissions, role profiles and the LLM/cost governance they set.
Operations / Ops Manager
Needs answers about stock, sales and outstanding balances now, without opening a ticket. Wants to ask in plain English, get a chart or table, and schedule the recurring ones to email or WhatsApp so their morning starts with the numbers.
Finance / Controller
Wants period-close and receivables questions answered fast, plus tightly controlled write actions and an audit trail. Cares that salary and margin fields can be masked before anything leaves for an external LLM provider.
Systems Integrator / IT Lead
Evaluating whether to build in-house or commission it. Wants a clean Frappe app they receive as source in a git repo, provider-agnostic LLM config, and something maintainable across v15/v16 upgrades rather than a black-box marketplace binary.
Visão geral da instalação
Baixe do ECOSIRE
Compre a licença em ecosire.com e baixe o ZIP do aplicativo ERPNext AI Copilot no painel da sua conta.
Adicione o aplicativo à sua bancada
Extraia o ZIP na pasta de aplicativos do seu banco ou execute `bench get-app` com o caminho para o aplicativo extraído.
Instale no seu site
Execute `bench --site SITE_NAME install-app APP_NAME` seguido de `bench Migra` para instalar ERPNext AI Copilot e aplicar seu esquema.
Ative sua licença
Abra as configurações de licença ECOSIRE em seu site e ative sua chave de licença. Requer os aplicativos gratuitos ecosire_connect e ecosire_license_client.
Como ERPNext AI Copilot se compara
| Critério | ECOSIRE | Construção personalizada | Concorrente | Odoo nativo |
|---|---|---|---|---|
| Natural-language querying | Curated intent catalog over the Frappe ORM, tuned to your DocTypes | Build the NL layer and safety yourself | Generic NL, often loosely mapped to your data | |
| Action execution (writes) | Whitelisted methods, confirm step, permission-gated + logged | Possible but you own all the guardrails | Usually read-only or limited | |
| Permission & role awareness | Every call through `frappe.has_permission` + role profile | Correct only if you wire it carefully | Varies; often bypasses granular perms | |
| LLM provider choice | OpenAI, Claude, DeepSeek or self-hosted, per environment | Your integration effort | Often locked to one vendor/API | |
| Data residency / masking | Local-model option + field-masking before external calls | Your responsibility to design | Typically routed to vendor cloud | |
| Scheduled NL reports | Frappe scheduler_events → email + WhatsApp | Build the scheduler + delivery yourself | Sometimes email only, fixed formats | |
| Ownership & source | Full source + git repo handover | You own it (and the build cost/time) | Closed binary / SaaS subscription | |
| Delivery & fit | Built to your instance, v15/v16, 2–4 weeks + UAT | Months of in-house build and testing | Instant install but generic fit |
Perguntas frequentes sobre ERPNext AI Copilot
+How long until we can use it? Is this an instant download?
No — it is build-to-order, not a marketplace download. After a short scoping call to confirm your DocTypes, roles, LLM provider and report cadences, typical delivery is 2–4 weeks from confirmed scope. We build against your Frappe/ERPNext version, test on a staging bench, run UAT, then install to production.
+Which LLM providers does it support, and does our data leave our servers?
It is provider-agnostic — OpenAI, Anthropic Claude, DeepSeek, or a self-hosted local model, selected per environment. If data residency is a hard requirement we can wire it to a local/self-hosted model so prompts never leave your infrastructure. Field-masking hooks can also redact sensitive fields (salaries, margins) before anything is sent to an external provider.
+Can it write to ERPNext, or is it read-only? Is that safe?
It can do both. Reads answer questions; writes create/update/submit documents through whitelisted server methods with a confirmation step. Both paths run through `frappe.has_permission` and the user's role profile, so the Copilot can never read or write anything that user couldn't do manually in the desk. Every action is logged to an audit DocType via hooks.py doc events.
+Does it generate SQL against our database?
No. To keep it safe, the LLM classifies each question into a curated catalog of pre-written, parameterized query intents resolved through the Frappe ORM — it does not generate free-form SQL against your database. Custom intents specific to your DocTypes are part of the build.
+Which ERPNext versions are supported?
Frappe/ERPNext v15 and v16. We build and test against the exact version and apps on your bench, so custom apps and customizations on your site are accounted for during scoping.
+What support and updates come after go-live?
Delivery includes a post-go-live support window for bug fixes and configuration adjustments, plus the full source in a git repository so your team (or ours) can extend it. Ongoing maintenance, new query intents, and compatibility work for future ERPNext upgrades are available as a follow-on support arrangement.
+How do scheduled reports get delivered?
A user describes a report once in plain English and sets the cadence; the Copilot registers it via Frappe `scheduler_events` and delivers the result to email and/or WhatsApp on schedule — for example a Monday-morning low-stock digest of items below reorder level.
Módulos Relacionados
Solicitar orçamento
ERPNext AI Copilot
A build-to-order in-app AI assistant for ERPNext that answers business questions, executes document actions, generates charts and schedules reports in plain English across any DocType. ECOSIRE scopes, builds, installs and supports it — request a quotation to start.
- Natural-language query over live ERPNext data (Selling, Stock, Accounts, HR) resolved through the Frappe ORM, not raw SQL against the database
- Curated catalog of parameterized query intents — the LLM classifies the question and fills validated parameters, so it never generates arbitrary SQL
- Permission-aware execution: every read and write runs through `frappe.has_permission` and the user's role profile, honoring User Permissions and DocType-level restrictions
- Action execution from chat — create, update, add comments to, or submit documents (e.g. Material Request, Lead, Expense Claim) via whitelisted server methods with a confirmation step