Hero - Build your bot

Sometimes our trigger may appear too generous. For example, consider the two different user inputs below, which both trigger the first flow created in our Longberry Baristas, [User asks about coffees we offer](/getting-started/your-first-flow), even though only the first one should:

>**User**: Which coffees do you serve?  
>**Bot**: We offer a variety of handcrafted coffee drinks - from espressos to macchiatos to flat whites and more. 
>
>**User**: Which **teas** do you serve?  
>**Bot**: We offer a variety of handcrafted coffee drinks - from espressos to macchiatos to flat whites and more.

What we need to do is to restrict the trigger from triggering too generously, so that the second input goes to another flow or to the [Safetynet](/studio/conversations/concepts/safetynet) fallback flow instead:

>**User**: Which **teas** do you serve?  
>**Bot**: I'm sorry but I didn't get that.

We will restrict the 'User asks about coffees we offer' flow from over-triggering by combining match requirements in addition to the class match in the trigger. This way, we can impose hand-picked restrictions on the [Class Match](/studio/flows/concepts/triggers#class). For example, we can restrict it to only trigger if certain words like 'coffee' or 'drink' are present in the input.

To accomplish this, we will need to do the following:
* Add a TLML Syntax Match to the trigger 
* Create a condition
* Add a confidence threshold

Once we're done, the final flow will look like this:
![combine-match-req](//images.ctfassets.net/2vbtnveccz5s/7m4dyeqNWK7bWxGzKf867V/b1435e84de6e5e9e3664036450b69969/combine-match-req.PNG)

## Add a TLML Syntax Match 
We will start off by doing the following:
1. Open the 'User asks about coffees we offer' flow that we [created earlier](/getting-started/your-first-flow) in edit mode. 
2. Select the Trigger 'Tell me about your coffee', which will open up the configuration panel.
3. Scroll down to the Match section and press 'Add' followed by 'TLML Syntax'.
4. Go ahead and name the TLML Syntax condition to `Restrict to only coffees and drinks` in order to more easily keep track of what the Syntax condition does. 
5. Paste in the following condition `(%COFFEE.NN.SYN/%DRINK.NN.LEX)`.

![1-add tlml syntax](//videos.ctfassets.net/2vbtnveccz5s/311MT5v66ju7PAWXJuURUx/0d2056a47370118571ca4b4ccec7a981/1-add_tlml_syntax.mp4)

## Add a confidence threshold
We will now add a confidence threshold to the trigger to ensure that it is only triggered when the machine learning algorithm is sufficiently confident.
1. Select the 'Tell me about your coffee' trigger.
2. In the 'Match' section, click on 'Add' followed up with 'Scripted Context'. This will allow you to add [Context](/studio/conversations/concepts/context) to your trigger.
3. Add the context 'Class Confidence Medium' from the drop-down menu.
4. Hit 'Save'.

![2-conf threshold](//videos.ctfassets.net/2vbtnveccz5s/2RGBsTF36g1N9mlaPuIyBF/e735abed7c35ec7f802f44d734f20b91/2-conf_threshold.mp4)

## Try it out!
Now, go to Tryout and give it a try! You should now get a similar answer as below. As long as you do not get the 'We offer a variety of handcrafted coffee drinks...' answer when asking for tea, you have succeeded!

>**User**: Which coffees do you serve?  
>**Bot**: We offer a variety of handcrafted coffee drinks - from espressos to macchiatos to flat whites and more. 
>
>**User**: Which **teas** do you serve?  
>**Bot**: I'm sorry but I didn't get that.


Build - Combine match requirements

Sometimes our trigger may appear too generous. For example, consider the two different user inputs below, which both trigger the first flow created in our Longberry Baristas, [User asks about coffees we offer](/getting-started/your-first-flow), even though only the first one should:

>**User**: Which coffees do you serve?  
>**Bot**: We offer a variety of handcrafted coffee drinks - from espressos to macchiatos to flat whites and more. 
>
>**User**: Which **teas** do you serve?  
>**Bot**: We offer a variety of handcrafted coffee drinks - from espressos to macchiatos to flat whites and more.

What we need to do is to restrict the trigger from triggering too generously, so that the second input goes to another flow or to the [Safetynet](/studio/conversations/concepts/safetynet) fallback flow instead:

>**User**: Which **teas** do you serve?  
>**Bot**: I'm sorry but I didn't get that.

We will restrict the 'User asks about coffees we offer' flow from over-triggering by combining match requirements in addition to the class match in the trigger. This way, we can impose hand-picked restrictions on the [Class Match](/studio/flows/concepts/triggers#class). For example, we can restrict it to only trigger if certain words like 'coffee' or 'drink' are present in the input.

To accomplish this, we will need to do the following:
* Add a TLML Syntax Match to the trigger 
* Create a condition
* Add a confidence threshold

Once we're done, the final flow will look like this:

![finished](//images.ctfassets.net/2vbtnveccz5s/4JCf5AO6EwpU4vcKApXbIs/1779fd0a79f957b809d6ba76c230726e/finished.PNG)

## Add a TLML Syntax Match 
We will start off by doing the following:
1. Open the 'User asks about coffees we offer' flow that we [created earlier](/getting-started/your-first-flow) in edit mode. 
2. Select the 'Add match requirement' below the trigger 'Tell me about your coffee'.
3. Scroll down to 'TLML Syntax' and add it.
4. Paste in the following condition `(%COFFEE.NN.SYN/%DRINK.NN.LEX)`.

![1-tlml-syntax](//videos.ctfassets.net/2vbtnveccz5s/3yce2orNyxr7fK2LosFSjC/f2e22b51ec35dca15ef48a0149d2bc79/1-tlml-syntax.mp4)

## Add a confidence threshold
We will now add a confidence threshold to the trigger to ensure that it is only triggered when the machine learning algorithm is sufficiently confident.
1. Select 'Add a match requirement' below the TLML Syntax condition.
2. Add a 'Global Scripted Context'. This will allow you to add [Context](/studio/conversations/concepts/context) to your trigger.
3. Add the context 'Class Confidence Medium' from the drop-down menu.
4. From the dropdown select '0.60'. 
5. Save your flow.

![2-create-and-save](//videos.ctfassets.net/2vbtnveccz5s/7qfwxTeENWzIfWVpRHLhvO/03d57b5c9d8ef8ac50d0092ad40016ce/2-create-and-save.mp4)

## Try it out!
Now, go to Tryout and give it a try! You should now get a similar answer as below. As long as you do not get the 'We offer a variety of handcrafted coffee drinks...' answer when asking for tea, you have succeeded!

>**User**: Which coffees do you serve?  
>**Bot**: We offer a variety of handcrafted coffee drinks - from espressos to macchiatos to flat whites and more. 
>
>**User**: Which **teas** do you serve?  
>**Bot**: I'm sorry but I didn't get that.


Studio Web - Build - Combine match requirements

Combine match requirements

Analyze your bot

Analyze Log Data

Analyzing sessions

Augmenters

Concepts

Extract values with Augmenters

How To

Metadata

Running custom queries

Counting coffees with Metadata

Reference

Teneo Query Language Cookbook

Teneo Query Language Reference Guide

Teneo Query Language Syntax Overview

Teneo Query Language

Data hierarchy

Event

Property

Session

Transaction

How to

Explore session statistics

Find stuck flows

Generate session logs

Locate and view a session

Make use of skip constraints

Make use of sub queries

Query variables

Troubleshoot the Safetynet

Use relative dates in queries

Query Syntax

Command

Constraint

Meta-parameter

Selection

Transformer

Build your bot

Bot design

Best practices

Data footprint

Encrypting user data in sessions

Flow checklist

Plan your bot

Starting a new Teneo project

Writing good answers

Writing good examples

Conversations

Context restrictions

Flow stack

Greeting message

Listeners

Safetynet

Trigger Ordering

Create a custom order group

Handle ambiguous inputs

Make your bot pro-active

Share information between flows

Use listeners

Flows

Bulk Import

Entities

Junctions

Outputs

Sub-Flows

Transitions

Intent triggers

Variables

Add a script to your flow

Branch at the beginning of a flow

Use TLML Syntax Match

Use a Sub-Flow

Use Bulk Import

Language Understanding

Annotations

Attached scripts

Language conditions

Language objects

Languages

Lexical resources

Libraries

Linguistic Modeling Language

Localization

Match requirements

Used words

Combine Match requirements

Create a solution in your language

Create your own language objects

Find language objects and entities

Localize a bot

Normalize the user's spelling

Optimize language conditions

Recognize plural and singular

Store what the user said

Advanced Condition Coding

Annotations Reference

Condition Syntax Reference

DateTime Handler

Engine Scripting API Reference

Input Processing Path

Language Object Reference

Scripting

Engine scripting API

Groovy basics

Integration manager

Resource file manager

Scripts

Add a Groovy class

Add an integration

Add files to your solution

Annotate user inputs

Anonymize user data

Define a scripted context

Populate output parameters

Store input parameters

Test your bot

Run automated tests

Test your bot with Botium

Dialog Tester

Deploy your bot

Engine API

Versioning and Publishing

Publish your bot

Version Flags

Work with Version Flags

SDK's

Android

JavaScript

Node.js

Getting started

After Match

Extract Entities

Class Manager

Introduction to transitions

Introduction to entities

Deal with Follow-ups

Dialogue and Context Model

Getting started with Teneo

Handle interruptions

Skip conditions

Teneo in 10 minutes

Flows and match requirements

Entities and After Match

Your First Flow

Your First Solution

Optimize your bot

Optimize classes

Improve the balance

Review Inputs

Refine your bot

Debug your bot in Tryout

Use Teneo's improvement tips

Troubleshooting

My flow doesn't trigger

My flow behaves unexpectedly

I see warnings in Tryout

Suggestions

root

Table of Contents