# Chatbot Intent Design Worksheet for ERP and Support Bots > Source: https://netray.co/tools/chatbot-intent-design-worksheet > Publisher: Netray (netray.co), AI and integration engineering for ERP and manufacturing systems. > Section: Free Tools ## Short answer Define each chatbot intent with example phrases, the system it reads, whether it can write, a confidence threshold and a fallback. ## Category ai-automation ## Audience - Business analyst - IT manager - Conversation designer ## Tool **Kind:** worksheet **Mode:** editable **Columns:** #### Intent name **Key:** intent **Type:** text #### Example user phrase **Key:** utterance **Type:** text #### Data source or API **Key:** source **Type:** text #### Action type **Key:** action **Type:** select **Options:** - Read only - Write with approval - Handoff to human - Static answer #### Identity needed **Key:** auth **Type:** select **Options:** - None - Verified employee - Verified customer - Approver role #### Training phrases written **Key:** phrases **Type:** number #### Expected asks per day **Key:** daily **Type:** number #### Minutes saved per ask **Key:** minutes **Type:** number #### Hours saved per month **Key:** saved **Type:** number **Expr:** daily * minutes * 22 / 60 **Format:** decimal #### Phrase target met (10+) **Key:** ready **Type:** number **Expr:** if(gte(phrases,10),1,0) **Format:** integer #### Fallback when unsure **Key:** fallback **Type:** text **Rows:** **Intent:** order_status **Utterance:** Where is my order 48213? **Source:** ERP sales order API **Action:** Read only **Auth:** Verified customer **Phrases:** 14 **Daily:** 80 **Minutes:** 4 **Fallback:** Offer to connect to customer service **Intent:** stock_check **Utterance:** How many of part BRK-1001 do we have? **Source:** ERP on-hand inventory **Action:** Read only **Auth:** Verified employee **Phrases:** 12 **Daily:** 30 **Minutes:** 3 **Fallback:** Ask for a part number again, then show search **Intent:** approve_po **Utterance:** Approve PO 5501 **Source:** ERP purchasing API **Action:** Write with approval **Auth:** Approver role **Phrases:** 9 **Daily:** 15 **Minutes:** 5 **Fallback:** Send a link to the approval screen **Intent:** report_machine_issue **Utterance:** Press 4 is making a grinding noise **Source:** CMMS work request API **Action:** Write with approval **Auth:** Verified employee **Phrases:** 6 **Daily:** 6 **Minutes:** 8 **Fallback:** Page the maintenance supervisor **Intent:** holiday_policy **Utterance:** How many leave days do I get? **Source:** HR policy document **Action:** Static answer **Auth:** None **Phrases:** 11 **Daily:** 10 **Minutes:** 2 **Fallback:** Link to the HR portal **Totals:** #### Total hours saved per month **Key:** saved **Agg:** sum **Format:** decimal #### Intents meeting phrase target **Key:** ready **Agg:** sum **Format:** integer #### Intents defined **Key:** intent **Agg:** count **Format:** integer **Summary:** #### Share of intents ready to train **Key:** ready_pct **Expr:** sum_ready / count * 100 **Format:** percent **Notes:** Hours saved assumes 22 working days per month and is an estimate for ranking intents, not a business case. Any intent that writes to a system should require approval and identity checks. ## Content **Intro:** A chatbot is only as good as the list of things it is meant to do. This worksheet makes you define each intent, the data it needs, the identity required and what happens when the bot is unsure, before any model is trained or prompted. **Sections:** #### How to use it **Body:** Collect real questions from ticket history, email and chat logs instead of guessing. Group them into intents, give each a short name, and paste a representative phrase. Note which system or API answers it, and whether the bot only reads or also changes data. Count your written training or test phrases, and estimate daily volume and the minutes each ask costs a human today. The sheet ranks intents by monthly hours saved so you can start with the ones that pay back. #### Read versus write **Body:** Start with read-only intents. Order status, stock checks and policy answers carry little risk and build trust. Any intent that creates or changes records, such as approving a purchase order or opening a work request, needs strong identity, a confirmation step and an audit trail. Mark those as write with approval and keep a human in the loop. Intents that touch pay, bank details or personal data deserve a separate security review. **Bullets:** - Authenticate before returning customer-specific data - Confirm before any write - Log intent, user, input and result - Never let the bot guess a document number #### Confidence and fallback **Body:** Every intent needs a defined fallback for low confidence, ambiguous input and system errors. Good fallbacks ask one clarifying question, offer a short menu, or hand over to a person with the conversation attached. With large language models the same logic applies: ground answers in the source system, show where the answer came from, and say when nothing was found. Review unmatched messages weekly and add the real ones as new intents. **Cta:** Netray builds grounded, on-prem chat agents over ERP data with read-only defaults. If a vendor chatbot is enough for your list, we will say so. **Faq:** #### How many training phrases does an intent need? **Answer:** Classic intent classifiers usually want ten or more varied phrases each, with more for similar intents. LLM based bots need fewer examples but still benefit from a test set of real questions. #### Which intents should I build first? **Answer:** High volume, low risk, read-only ones with a clean API behind them, such as order status or stock lookup. They show value quickly and give you real usage data. #### Can one bot serve WhatsApp and Teams? **Answer:** Yes, with a channel layer that formats replies per platform. Keep intent logic separate from the channel so you design it once. #### What is a safe confidence threshold? **Answer:** It depends on the model and the cost of a wrong answer. Set a higher threshold for write actions, test against real phrases, and tune from logs rather than picking a number up front. ## Search terms chatbot intent design template, chatbot intent worksheet, intent mapping spreadsheet, chatbot requirements template, erp chatbot use cases list, conversation design worksheet, whatsapp chatbot intents list, teams bot intent planning --- Talk to an engineer: https://netray.co/contact?intent=erp_ai | Machine catalog: https://netray.co/agent/catalog.json