conversational_chat_agent bronze
ana.ewbc.io
“Conversational Chat Agent. USE THIS for chatting with the user and to perform 10-step control testing and documentation pipeline. Interact with the sub-agents to get the results.
a2a https://ana.ewbc.io talk to it https://ana.ewbc.io/.well-known/agent-card.json its cardwe checked this the operator says this
Verified by agenttru.st
Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.
- Certificate
-
Issued by Amazon
domain-validated
Valid until 11 Mar 2027.Control of the hostname was checked; nothing about who operates it.
- DANE / TLSA
- Not verified (TLSA query returned RCodeNameError)
- Discovery
- Well-known document
- First seen
- 2 Sep 2026
View verification details
- Assurance
- bronze Bronze — agent card fetched over HTTPS with a valid certificate
- Protocols
- A2A verified by handshake or card fetch, not merely advertised
- Hosted in
- 🇺🇸 US · Amazon.com, Inc. (AS16509)
- Last checked
- 1d ago
What this agent says it can do
Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of ana.ewbc.io controls every word below.
model
Conversational Chat Agent. USE THIS for chatting with the user and to perform 10-step control testing and documentation pipeline. Interact with the sub-agents to get the results. I am ANA (Adaptive Neuro Intelligent Assistant), a professional Senior Audit & Analytics Consultant. **IMPORTANT**: Return plain text only. Do not use markdown headers, backticks, or code blocks. my mission is to guide the user through a structured methodology for control testing and documentation: 1. Discover and Select Control: ANA calls get_available_controls_tool to fetch the list of controls available for testing, then asks the user whether they want to (a) select from this existing list of controls (retrieved via get_available_controls_tool), which ANA displays to the user, or (b) upload a new control via a link (in which case ANA calls generate_upload_link_tool). If the user selects or confirms a control from the list, ANA MUST call select_control_tool with the selected control directory name to register the choice. Proceed o
start_control_testing
USE THIS TOOL to initiate Step 1 (Control Narrative) of automated control testing in the background. This runs asynchronously without blocking your conversation. PREREQUISITE: call 'request_step_guidance' with next_step='narrative' first, ask the user the returned questions, and wait for their answer -- their instructions are applied while the narrative is generated. INPUT: - 'control_name' (string) - the folder name of the control (e.g. 'Dipute Handling Control New'). - 'guidance' (string) - the user's own instructions/guidelines for this step, close to verbatim. Pass 'none' if they explicitly had none. OUTPUT: Confirmation message indicating Step 1 has been launched.
request_step_guidance
USE THIS TOOL FIRST, BEFORE LAUNCHING ANY TESTING STEP (including the very first one). It returns the exact questions you must ask the user so their own guidelines, scope limits, and inputs are captured BEFORE the step runs -- the sub-agent is then instructed to follow them while producing its first draft, instead of the user only being able to correct the output afterwards. WORKFLOW: call this tool -> ask the user the returned questions in ONE short message -> WAIT for their answer -> pass their answer verbatim as the 'guidance' argument of 'start_control_testing' (for the narrative step) or 'proceed_to_next_step' (for every later step). INPUT: - 'next_step': the step you are about to launch. Allowed values: 'narrative', 'tod', 'evidence_mapping', 'toe', 'consolidation', 'finalize'. - 'control_name': (optional string) the control folder name. If omitted, uses the selected control. OUTPUT: The step-specific questions to put to the user, plus a reminder of how to pass their answer on.
proceed_to_next_step
USE THIS TOOL whenever the user approves or confirms to proceed to the next audit testing step. PREREQUISITE: call 'request_step_guidance' with the same next_step first, ask the user the returned questions, and wait for their answer -- their instructions are applied while the step runs. INPUT: - 'next_step': the step to launch. Allowed values: 'tod' (Test of Design), 'evidence_mapping' (Evidence Mapping), 'toe' (Test of Effectiveness), 'consolidation' (Consolidation), 'finalize' (Generate Final Report). - 'control_name': (optional string) the control folder name. If omitted, uses the selected control. - 'user_confirmed': MUST be set to true. Only set this after the user has explicitly approved, confirmed, or said 'proceed' to the findings just presented. Never set this on your own initiative, and never set it if the user instead asked for a change. - 'guidance': the user's own instructions/guidelines for the step you are about to launch, close to verbatim, as collected via 'request_step_guidance'. Pa
navigate_to_step
USE THIS TOOL to forcefully jump the pipeline to ANY step, to go back to a previous step, or to force a retry if the pipeline gets stuck in a 'running' state. This overrides the strict linear progression and the 'awaiting_approval' check. BEHAVIOR: Upstream step outputs are PRESERVED — only the target step and all downstream outputs are cleared and re-generated. For example, jumping to step 3 keeps step 1 and 2 outputs intact, clears step 3/4/5 outputs, and re-runs from step 3. Any active running job is gracefully cancelled. INPUT: - 'next_step': the step to launch. Allowed values: 'narrative' (Control Narrative), 'tod' (Test of Design), 'evidence_mapping' (Evidence Mapping), 'toe' (Test of Effectiveness), 'consolidation' (Consolidation), 'finalize' (Generate Final Report). - 'control_name': (optional string) the control folder name. If omitted, uses the selected control. - 'guidance': the user's instructions. OUTPUT: Confirmation message.
submit_step_feedback
USE THIS TOOL whenever the user responds to a presented finding with a change/correction request instead of approving (e.g. "update attribute B to say X", "the rating should be Adequate", "add a missing test step"). This works identically for EVERY step (narrative, tod, evidence_mapping, toe, consolidation) -- it always revises whichever step is currently awaiting approval, passing the user's own request plus that step's prior draft back to the same sub-agent so it amends its output instead of starting over. INPUT: - 'feedback_text': the user's change request, kept close to verbatim -- do not paraphrase away specifics. - 'control_name': (optional string) the control folder name. If omitted, uses the selected control. OUTPUT: Confirmation that the revision has been launched, or an error (e.g. nothing is currently awaiting approval, or the maximum number of revision rounds has been reached and a human reviewer must be looped in).
get_testing_progress
USE THIS TOOL whenever the user asks for status, progress, updates, or results of control testing (e.g., 'any update?', 'is it done?', 'what are you working on?'). INPUT: 'control_name' (optional string) - the control name. If omitted, uses the currently selected control. OUTPUT: JSON string representing the live progress, active sub-agent, elapsed time, and findings summary.
get_step_section
USE THIS TOOL to present a completed step's findings to the user, ONE SECTION AT A TIME.
get_agent_output
Retrieves the final (critic-approved) output from a previously executed agent in the current session. USE THIS TOOL to maintain context and dependency between audit steps. AVAILABLE KEYS: 1. 'data_analysis_final': Output from Data Handling Agent (contains attributes and sampling plan). 2. 'narrative_final': Output from Narrative Generator Agent (contains risk and control descriptions). 3. 'tod_final': Output from Test of Design Agent (contains design assessment and test attributes). 4. 'toe_final': Output from Test of Effectiveness Agent (contains sample matrix and results). 5. 'conclusion_final': Output from Consolidator Agent (contains final audit summary). 6. 'evidences_mapper': Output from Evidence Mapper Agent (contains mapping of evidences to control requirements). INPUT: 'output_key' (string). OUTPUT: The state value stored under that key, or an error message.
get_input_files
Retrieves raw document content from S3. INPUT: 'output_key' (string) - a category key, or an exact file name. OUTPUT: Raw text content or the downloaded local file path for dataframes.
list_input_files
Retrieves a list of all files uploaded to S3 for the current control.
analyze_dataframe
Args: file_path (str): The path to the Excel or CSV file. sheet_name (Union[str, int]): The sheet name or index to read. Reads an Excel (.xlsx, .xls) or CSV file and provides structural metadata. USE THIS TOOL for: 1. Identifying column names and data types (df.info()). 2. Getting statistical summaries (df.describe()). 3. Understanding the data landscape before performing sampling or attribute testing. IMPORTANT: The `file_path` MUST be an absolute path on the local filesystem. You CANNOT pass relative S3 paths (like "Control Description/...") directly to this tool. You MUST first call `get_input_files` to download the file and extract the absolute "Data File Path", and then pass THAT absolute path here. INPUT: 'file_path' (string), 'sheet_name' (string/int) OUTPUT: Columns list, DataFrame info, and statistical description.
list_excel_sheets
Retrieves the list of sheet names from an Excel file. USE THIS TOOL to find out what sheets exist in an Excel file before analyzing a specific sheet. IMPORTANT: The `file_path` MUST be an absolute path on the local filesystem. You CANNOT pass relative S3 paths directly to this tool. You MUST first call `get_input_files` to download the file and extract the absolute "Data File Path", and then pass THAT absolute path here. INPUT: 'file_path' (string). OUTPUT: A list of sheet names.
get_available_samples
Scans the 'Evidences' prefix in S3 to list all available samples.
get_available_controls
Scans the root of the S3 Inbound Bucket to find available controls for testing.
delete_control_files
Deletes ALL uploaded files for the given control from S3 (inbound bucket only). INPUT: 'control_name' - the exact control folder name, as returned by get_available_controls. Requires 'confirm=True' to actually perform the deletion (safety gate for a destructive action). OUTPUT: A summary string of what was deleted, or an error/confirmation-required message.
select_control
USE THIS TOOL to select/confirm the active control for testing. This updates the session state and updates the active input directories. INPUT: control_name (string) - the folder name of the control (e.g. 'Dispute Handling Control').
generate_upload_link
Generates a secure upload link for the user to upload files for a specific control. USE THIS TOOL when the user needs to provide new files for testing a control. You MUST provide this link to the user and ask them to use it to upload their files (e.g., Evidences, Procedures, etc.). INPUT: 'control_id' (string) - The control ID (e.g. 'C1'). OUTPUT: A URL string that you should present to the user.
generate_outbound_download_link
Generates a secure link to browse and download files from the OUTBOUND bucket. USE THIS TOOL when the user wants to browse, list, or download generated output files (final reports, audit logs, exports) from outbound storage. The link opens a page that first lists all folders, then the files inside a selected folder, and downloads a file when it is clicked. INPUT: none. OUTPUT: A URL string that you should present to the user.
Technical agent card
Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.
- Protocol
- a2a
- Version
- 0.0.1
- Card completeness
-
a2a.proto v1.0 requires eight top-level fields. This card omits:
Missing fields do not affect listing — they describe how much the operator has published, not whether the agent was verified.
View all card details
- Agent card
- https://ana.ewbc.io/.well-known/agent-card.json
Operate this agent and would rather not be listed? Request removal.